{"url":"/sota/domain-generalization-on-vizwiz","task":{"name":"Domain Generalization","url":"/task/domain-generalization","note":null},"dataset":{"name":"VizWiz-Classification","url":"/dataset/vizwiz-classification"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"The idea of **Domain Generalization** is to learn from one or multiple training domains, to extract a domain-agnostic model which can be applied to an unseen domain\n\n\n<span class=\"description-source\">Source: [Diagram Image Retrieval using Sketch-Based Deep Learning and Transfer Learning ](https://arxiv.org/abs/2004.10780)</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy - All Images","Accuracy - Corrupted Images","Accuracy - Clean Images"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy - All Images":"higher","Accuracy - Corrupted Images":"higher","Accuracy - Clean Images":"higher"}},"counts":{"rows":90,"rows_with_code":90,"rows_with_paper_page":90,"rows_dated":90,"rows_using_additional_data":4},"rows":[{"rank_in_archive_order":1,"model":"VOLO-D5","metrics":{"Accuracy - All Images":"57.2","Accuracy - Clean Images":"59.7","Accuracy - Corrupted Images":"51.8"},"uses_additional_data":false,"paper_date":"2021-06-24","paper":"/paper/volo-vision-outlooker-for-visual-recognition","paper_url":"https://arxiv.org/abs/2106.13112v2","paper_title":"VOLO: Vision Outlooker for Visual Recognition","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"ConvNeXt-B","metrics":{"Accuracy - All Images":"53.5","Accuracy - Clean Images":"56","Accuracy - Corrupted Images":"46.9"},"uses_additional_data":true,"paper_date":"2022-01-10","paper":"/paper/a-convnet-for-the-2020s","paper_url":"https://arxiv.org/abs/2201.03545v2","paper_title":"A ConvNet for the 2020s","code":"https://github.com/keras-team/keras/blob/master/keras/applications/convnext.py","n_code_links":54,"syntology":{"n_ran":54,"n_unverified":26,"n_samples":80,"n_pointer_only_licence":11}},{"rank_in_archive_order":3,"model":"ResNeXt-101 32x16d","metrics":{"Accuracy - All Images":"51.7","Accuracy - Clean Images":"54.8","Accuracy - Corrupted Images":"48.1"},"uses_additional_data":true,"paper_date":"2016-11-16","paper":"/paper/aggregated-residual-transformations-for-deep","paper_url":"http://arxiv.org/abs/1611.05431v2","paper_title":"Aggregated Residual Transformations for Deep Neural Networks","code":"https://github.com/pytorch/vision","n_code_links":61,"syntology":{"n_ran":34,"n_unverified":46,"n_samples":80,"n_pointer_only_licence":13}},{"rank_in_archive_order":4,"model":"EfficientNet-B8 (advprop+autoaug)","metrics":{"Accuracy - All Images":"50.5","Accuracy - Clean Images":"53.2","Accuracy - Corrupted Images":"45.8"},"uses_additional_data":false,"paper_date":"2019-11-21","paper":"/paper/adversarial-examples-improve-image","paper_url":"https://arxiv.org/abs/1911.09665v2","paper_title":"Adversarial Examples Improve Image Recognition","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"EfficientNet-B7 (advprop+autoaug)","metrics":{"Accuracy - All Images":"49.7","Accuracy - Clean Images":"52","Accuracy - Corrupted Images":"45"},"uses_additional_data":false,"paper_date":"2019-11-21","paper":"/paper/adversarial-examples-improve-image","paper_url":"https://arxiv.org/abs/1911.09665v2","paper_title":"Adversarial Examples Improve Image Recognition","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"EfficientNet-B6 (advprop+autoaug)","metrics":{"Accuracy - All Images":"49.6","Accuracy - Clean Images":"53.2","Accuracy - Corrupted Images":"44.7"},"uses_additional_data":false,"paper_date":"2019-11-21","paper":"/paper/adversarial-examples-improve-image","paper_url":"https://arxiv.org/abs/1911.09665v2","paper_title":"Adversarial Examples Improve Image Recognition","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"EfficientNet-B5 (advprop+autoaug)","metrics":{"Accuracy - All Images":"49.1","Accuracy - Clean Images":"51.7","Accuracy - Corrupted Images":"44"},"uses_additional_data":false,"paper_date":"2019-11-21","paper":"/paper/adversarial-examples-improve-image","paper_url":"https://arxiv.org/abs/1911.09665v2","paper_title":"Adversarial Examples Improve Image Recognition","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"ViT-16/L-224","metrics":{"Accuracy - All Images":"49"},"uses_additional_data":true,"paper_date":"2020-10-22","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","paper_url":"https://arxiv.org/abs/2010.11929v2","paper_title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","code":"https://github.com/huggingface/transformers","n_code_links":158,"syntology":{"n_ran":281,"n_unverified":138,"n_samples":419,"n_pointer_only_licence":154}},{"rank_in_archive_order":9,"model":"ResNet-50 (gn)","metrics":{"Accuracy - All Images":"48.9","Accuracy - Clean Images":"44.4","Accuracy - Corrupted Images":"39.1"},"uses_additional_data":false,"paper_date":"2021-10-01","paper":"/paper/resnet-strikes-back-an-improved-training","paper_url":"https://arxiv.org/abs/2110.00476v1","paper_title":"ResNet strikes back: An improved training procedure in timm","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":14,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"EfficientNet-B4 (advprop+autoaug)","metrics":{"Accuracy - All Images":"48.1","Accuracy - Clean Images":"51.4","Accuracy - Corrupted Images":"42.5"},"uses_additional_data":false,"paper_date":"2019-11-21","paper":"/paper/adversarial-examples-improve-image","paper_url":"https://arxiv.org/abs/1911.09665v2","paper_title":"Adversarial Examples Improve Image Recognition","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"ResNet-152","metrics":{"Accuracy - All Images":"47.5","Accuracy - Clean Images":"51.3","Accuracy - Corrupted Images":"43.3"},"uses_additional_data":false,"paper_date":"2015-12-10","paper":"/paper/deep-residual-learning-for-image-recognition","paper_url":"http://arxiv.org/abs/1512.03385v1","paper_title":"Deep Residual Learning for Image Recognition","code":"https://github.com/tensorflow/models/tree/master/research/deeplab","n_code_links":484,"syntology":{"n_ran":230,"n_unverified":147,"n_samples":377,"n_pointer_only_licence":187}},{"rank_in_archive_order":12,"model":"ResNet-101","metrics":{"Accuracy - All Images":"46.3","Accuracy - Clean Images":"50.1","Accuracy - Corrupted Images":"40.5"},"uses_additional_data":false,"paper_date":"2015-12-10","paper":"/paper/deep-residual-learning-for-image-recognition","paper_url":"http://arxiv.org/abs/1512.03385v1","paper_title":"Deep Residual Learning for Image Recognition","code":"https://github.com/tensorflow/models/tree/master/research/deeplab","n_code_links":484,"syntology":{"n_ran":230,"n_unverified":147,"n_samples":377,"n_pointer_only_licence":187}},{"rank_in_archive_order":13,"model":"EfficientNet-B6 (autoaug)","metrics":{"Accuracy - All Images":"45.8","Accuracy - Clean Images":"50.7","Accuracy - Corrupted Images":"39.3"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/autoaugment-learning-augmentation-strategies","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Cubuk_AutoAugment_Learning_Augmentation_Strategies_From_Data_CVPR_2019_paper.html","paper_title":"AutoAugment: Learning Augmentation Strategies From Data","code":"https://github.com/mindspore-ai/models/blob/master/research/cv/autoaugment","n_code_links":3,"syntology":null},{"rank_in_archive_order":14,"model":"EfficientNet-B5 (autoaug)","metrics":{"Accuracy - All Images":"45.7","Accuracy - Clean Images":"50.2","Accuracy - Corrupted Images":"39.8"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/autoaugment-learning-augmentation-strategies","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Cubuk_AutoAugment_Learning_Augmentation_Strategies_From_Data_CVPR_2019_paper.html","paper_title":"AutoAugment: Learning Augmentation Strategies From Data","code":"https://github.com/mindspore-ai/models/blob/master/research/cv/autoaugment","n_code_links":3,"syntology":null},{"rank_in_archive_order":15,"model":"EfficientNet-B3 (advprop+autoaug)","metrics":{"Accuracy - All Images":"45.5","Accuracy - Clean Images":"49.5","Accuracy - Corrupted Images":"39.8"},"uses_additional_data":false,"paper_date":"2019-11-21","paper":"/paper/adversarial-examples-improve-image","paper_url":"https://arxiv.org/abs/1911.09665v2","paper_title":"Adversarial Examples Improve Image Recognition","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"EfficientNet-B7 (autoaug)","metrics":{"Accuracy - All Images":"45","Accuracy - Clean Images":"49.9","Accuracy - Corrupted Images":"39.1"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/autoaugment-learning-augmentation-strategies","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Cubuk_AutoAugment_Learning_Augmentation_Strategies_From_Data_CVPR_2019_paper.html","paper_title":"AutoAugment: Learning Augmentation Strategies From Data","code":"https://github.com/mindspore-ai/models/blob/master/research/cv/autoaugment","n_code_links":3,"syntology":null},{"rank_in_archive_order":17,"model":"EfficientNet-B7 (randaug)","metrics":{"Accuracy - All Images":"45","Accuracy - Clean Images":"48.7","Accuracy - Corrupted Images":"38.9"},"uses_additional_data":false,"paper_date":"2019-09-30","paper":"/paper/randaugment-practical-data-augmentation-with","paper_url":"https://arxiv.org/abs/1909.13719v2","paper_title":"RandAugment: Practical automated data augmentation with a reduced search space","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":19,"syntology":{"n_ran":58,"n_unverified":7,"n_samples":65,"n_pointer_only_licence":17}},{"rank_in_archive_order":18,"model":"EfficientNet-B4 (autoaug)","metrics":{"Accuracy - All Images":"44.3","Accuracy - Clean Images":"48.6","Accuracy - Corrupted Images":"38.2"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/autoaugment-learning-augmentation-strategies","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Cubuk_AutoAugment_Learning_Augmentation_Strategies_From_Data_CVPR_2019_paper.html","paper_title":"AutoAugment: Learning Augmentation Strategies From Data","code":"https://github.com/mindspore-ai/models/blob/master/research/cv/autoaugment","n_code_links":3,"syntology":null},{"rank_in_archive_order":19,"model":"EfficientNet-B2 (advprop+autoaug)","metrics":{"Accuracy - All Images":"44.3","Accuracy - Clean Images":"48","Accuracy - Corrupted Images":"38.2"},"uses_additional_data":false,"paper_date":"2019-11-21","paper":"/paper/adversarial-examples-improve-image","paper_url":"https://arxiv.org/abs/1911.09665v2","paper_title":"Adversarial Examples Improve Image Recognition","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"ResNet-50","metrics":{"Accuracy - All Images":"42.9","Accuracy - Clean Images":"47.7","Accuracy - Corrupted Images":"37.1"},"uses_additional_data":false,"paper_date":"2015-12-10","paper":"/paper/deep-residual-learning-for-image-recognition","paper_url":"http://arxiv.org/abs/1512.03385v1","paper_title":"Deep Residual Learning for Image Recognition","code":"https://github.com/tensorflow/models/tree/master/research/deeplab","n_code_links":484,"syntology":{"n_ran":230,"n_unverified":147,"n_samples":377,"n_pointer_only_licence":187}},{"rank_in_archive_order":21,"model":"EfficientNet-B5","metrics":{"Accuracy - All Images":"42.8","Accuracy - Clean Images":"47.3","Accuracy - Corrupted Images":"37"},"uses_additional_data":false,"paper_date":"2019-05-28","paper":"/paper/efficientnet-rethinking-model-scaling-for","paper_url":"https://arxiv.org/abs/1905.11946v5","paper_title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","code":"https://github.com/ultralytics/yolov5","n_code_links":144,"syntology":{"n_ran":171,"n_unverified":131,"n_samples":302,"n_pointer_only_licence":112}},{"rank_in_archive_order":22,"model":"EfficientNet-B3 (autoaug)","metrics":{"Accuracy - All Images":"42.6","Accuracy - Clean Images":"47.5","Accuracy - Corrupted Images":"34.9"},"uses_additional_data":false,"paper_date":"2018-05-24","paper":"/paper/autoaugment-learning-augmentation-policies","paper_url":"http://arxiv.org/abs/1805.09501v3","paper_title":"AutoAugment: Learning Augmentation Policies from Data","code":"https://github.com/tensorflow/models/tree/master/research/autoaugment","n_code_links":33,"syntology":{"n_ran":6,"n_unverified":37,"n_samples":43,"n_pointer_only_licence":2}},{"rank_in_archive_order":23,"model":"EfficientNet-B1 (advprop+autoaug)","metrics":{"Accuracy - All Images":"42.4","Accuracy - Clean Images":"46.7","Accuracy - Corrupted Images":"36.2"},"uses_additional_data":false,"paper_date":"2019-11-21","paper":"/paper/adversarial-examples-improve-image","paper_url":"https://arxiv.org/abs/1911.09665v2","paper_title":"Adversarial Examples Improve Image Recognition","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":24,"model":"ResNet-50 (augmix)","metrics":{"Accuracy - All Images":"42.2","Accuracy - Clean Images":"46.4","Accuracy - Corrupted Images":"35.9"},"uses_additional_data":false,"paper_date":"2019-12-05","paper":"/paper/augmix-a-simple-data-processing-method-to","paper_url":"https://arxiv.org/abs/1912.02781v2","paper_title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":15,"syntology":{"n_ran":43,"n_unverified":8,"n_samples":51,"n_pointer_only_licence":25}},{"rank_in_archive_order":25,"model":"EfficientNet-B5 (randaug)","metrics":{"Accuracy - All Images":"42.1","Accuracy - Clean Images":"47.3","Accuracy - Corrupted Images":"35.5"},"uses_additional_data":false,"paper_date":"2019-09-30","paper":"/paper/randaugment-practical-data-augmentation-with","paper_url":"https://arxiv.org/abs/1909.13719v2","paper_title":"RandAugment: Practical automated data augmentation with a reduced search space","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":19,"syntology":{"n_ran":58,"n_unverified":7,"n_samples":65,"n_pointer_only_licence":17}},{"rank_in_archive_order":26,"model":"ResNet-101 (lpf3)","metrics":{"Accuracy - All Images":"41.7","Accuracy - Clean Images":"46.1","Accuracy - Corrupted Images":"35.7"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":27,"model":"EfficientNet-B4","metrics":{"Accuracy - All Images":"41.7","Accuracy - Clean Images":"46.4","Accuracy - Corrupted Images":"35.6"},"uses_additional_data":false,"paper_date":"2019-05-28","paper":"/paper/efficientnet-rethinking-model-scaling-for","paper_url":"https://arxiv.org/abs/1905.11946v5","paper_title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","code":"https://github.com/ultralytics/yolov5","n_code_links":144,"syntology":{"n_ran":171,"n_unverified":131,"n_samples":302,"n_pointer_only_licence":112}},{"rank_in_archive_order":28,"model":"EfficientNet-B2 (autoaug)","metrics":{"Accuracy - All Images":"41.6","Accuracy - Clean Images":"45.8","Accuracy - Corrupted Images":"34.3"},"uses_additional_data":false,"paper_date":"2018-05-24","paper":"/paper/autoaugment-learning-augmentation-policies","paper_url":"http://arxiv.org/abs/1805.09501v3","paper_title":"AutoAugment: Learning Augmentation Policies from Data","code":"https://github.com/tensorflow/models/tree/master/research/autoaugment","n_code_links":33,"syntology":{"n_ran":6,"n_unverified":37,"n_samples":43,"n_pointer_only_licence":2}},{"rank_in_archive_order":29,"model":"ResNet-50 (lpf5)","metrics":{"Accuracy - All Images":"41.5","Accuracy - Clean Images":"45.3","Accuracy - Corrupted Images":"35.2"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":30,"model":"ResNet-50 (deepaugment)","metrics":{"Accuracy - All Images":"41.3","Accuracy - Clean Images":"46","Accuracy - Corrupted Images":"34.9"},"uses_additional_data":false,"paper_date":"2020-06-29","paper":"/paper/the-many-faces-of-robustness-a-critical","paper_url":"https://arxiv.org/abs/2006.16241v3","paper_title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","code":"https://github.com/hendrycks/imagenet-r","n_code_links":1,"syntology":{"n_ran":13,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":31,"model":"ResNet-101 (lpf2)","metrics":{"Accuracy - All Images":"41.1","Accuracy - Clean Images":"45.2","Accuracy - Corrupted Images":"35.1"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":32,"model":"ResNet-101 (lpf5)","metrics":{"Accuracy - All Images":"41","Accuracy - Clean Images":"45.8","Accuracy - Corrupted Images":"34.8"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":33,"model":"EfficientNet-B3","metrics":{"Accuracy - All Images":"40.7","Accuracy - Clean Images":"45.3","Accuracy - Corrupted Images":"34.2"},"uses_additional_data":false,"paper_date":"2019-05-28","paper":"/paper/efficientnet-rethinking-model-scaling-for","paper_url":"https://arxiv.org/abs/1905.11946v5","paper_title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","code":"https://github.com/ultralytics/yolov5","n_code_links":144,"syntology":{"n_ran":171,"n_unverified":131,"n_samples":302,"n_pointer_only_licence":112}},{"rank_in_archive_order":34,"model":"EfficientNet-B0 (advprop+autoaug)","metrics":{"Accuracy - All Images":"40.5","Accuracy - Clean Images":"44.9","Accuracy - Corrupted Images":"34.2"},"uses_additional_data":false,"paper_date":"2019-11-21","paper":"/paper/adversarial-examples-improve-image","paper_url":"https://arxiv.org/abs/1911.09665v2","paper_title":"Adversarial Examples Improve Image Recognition","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":35,"model":"ResNet-50 (deepaugment+augmix)","metrics":{"Accuracy - All Images":"40.3","Accuracy - Clean Images":"44.5","Accuracy - Corrupted Images":"34.1"},"uses_additional_data":false,"paper_date":"2020-06-29","paper":"/paper/the-many-faces-of-robustness-a-critical","paper_url":"https://arxiv.org/abs/2006.16241v3","paper_title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","code":"https://github.com/hendrycks/imagenet-r","n_code_links":1,"syntology":{"n_ran":13,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":36,"model":"ResNet-50 (lpf2)","metrics":{"Accuracy - All Images":"40.3","Accuracy - Clean Images":"45.1","Accuracy - Corrupted Images":"33.4"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":37,"model":"ResNet-50 (lpf3)","metrics":{"Accuracy - All Images":"40","Accuracy - Clean Images":"44.7","Accuracy - Corrupted Images":"34.3"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":38,"model":"ResNet-26-D","metrics":{"Accuracy - All Images":"39.7","Accuracy - Clean Images":"43.5","Accuracy - Corrupted Images":"35.8"},"uses_additional_data":false,"paper_date":"2018-12-04","paper":"/paper/bag-of-tricks-for-image-classification-with","paper_url":"http://arxiv.org/abs/1812.01187v2","paper_title":"Bag of Tricks for Image Classification with Convolutional Neural Networks","code":"https://github.com/PaddlePaddle/PaddleOCR","n_code_links":28,"syntology":{"n_ran":4,"n_unverified":11,"n_samples":15,"n_pointer_only_licence":5}},{"rank_in_archive_order":39,"model":"EfficientNet-B1 (autoaug)","metrics":{"Accuracy - All Images":"39.7","Accuracy - Clean Images":"44.4","Accuracy - Corrupted Images":"32.8"},"uses_additional_data":false,"paper_date":"2018-05-24","paper":"/paper/autoaugment-learning-augmentation-policies","paper_url":"http://arxiv.org/abs/1805.09501v3","paper_title":"AutoAugment: Learning Augmentation Policies from Data","code":"https://github.com/tensorflow/models/tree/master/research/autoaugment","n_code_links":33,"syntology":{"n_ran":6,"n_unverified":37,"n_samples":43,"n_pointer_only_licence":2}},{"rank_in_archive_order":40,"model":"ResNet-50 (SIN_IN_IN)","metrics":{"Accuracy - All Images":"39.2","Accuracy - Clean Images":"44.6","Accuracy - Corrupted Images":"32.4"},"uses_additional_data":false,"paper_date":"2018-11-29","paper":"/paper/imagenet-trained-cnns-are-biased-towards","paper_url":"https://arxiv.org/abs/1811.12231v3","paper_title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","code":"https://github.com/rgeirhos/texture-vs-shape","n_code_links":7,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":41,"model":"ResNet-50 (IN-C)","metrics":{"Accuracy - All Images":"38.8","Accuracy - Clean Images":"42.9","Accuracy - Corrupted Images":"33.6"},"uses_additional_data":false,"paper_date":"2020-07-01","paper":"/paper/measuring-robustness-to-natural-distribution","paper_url":"https://arxiv.org/abs/2007.00644v2","paper_title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","code":"https://github.com/modestyachts/imagenet-testbed","n_code_links":1,"syntology":null},{"rank_in_archive_order":42,"model":"ResNet-50 (IN-C_brightness)","metrics":{"Accuracy - All Images":"38.8","Accuracy - Clean Images":"43.5","Accuracy - Corrupted Images":"32.5"},"uses_additional_data":false,"paper_date":"2020-07-01","paper":"/paper/measuring-robustness-to-natural-distribution","paper_url":"https://arxiv.org/abs/2007.00644v2","paper_title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","code":"https://github.com/modestyachts/imagenet-testbed","n_code_links":1,"syntology":null},{"rank_in_archive_order":43,"model":"DenseNet121 (lpf5)","metrics":{"Accuracy - All Images":"38.7","Accuracy - Clean Images":"42.7","Accuracy - Corrupted Images":"32"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":44,"model":"ResNet-34 (lpf2)","metrics":{"Accuracy - All Images":"38.3","Accuracy - Clean Images":"42.8","Accuracy - Corrupted Images":"32.4"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":45,"model":"DenseNet-121 (lpf3)","metrics":{"Accuracy - All Images":"38.3","Accuracy - Clean Images":"42.8","Accuracy - Corrupted Images":"32.3"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":46,"model":"ResNet-34 (lpf3)","metrics":{"Accuracy - All Images":"38.3","Accuracy - Clean Images":"42.9","Accuracy - Corrupted Images":"31.9"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":47,"model":"DenseNet-121 (lpf2)","metrics":{"Accuracy - All Images":"38.3","Accuracy - Clean Images":"43.1","Accuracy - Corrupted Images":"31.7"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":48,"model":"ResNet-50 (IN-C_spatter)","metrics":{"Accuracy - All Images":"38.3","Accuracy - Clean Images":"42.7","Accuracy - Corrupted Images":"31.4"},"uses_additional_data":false,"paper_date":"2020-07-01","paper":"/paper/measuring-robustness-to-natural-distribution","paper_url":"https://arxiv.org/abs/2007.00644v2","paper_title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","code":"https://github.com/modestyachts/imagenet-testbed","n_code_links":1,"syntology":null},{"rank_in_archive_order":49,"model":"ResNet-50 (SIN_IN)","metrics":{"Accuracy - All Images":"38.2","Accuracy - Clean Images":"42.7","Accuracy - Corrupted Images":"32.5"},"uses_additional_data":false,"paper_date":"2018-11-29","paper":"/paper/imagenet-trained-cnns-are-biased-towards","paper_url":"https://arxiv.org/abs/1811.12231v3","paper_title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","code":"https://github.com/rgeirhos/texture-vs-shape","n_code_links":7,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":50,"model":"ResNet-50 (IN-C_saturate)","metrics":{"Accuracy - All Images":"38.2","Accuracy - Clean Images":"42.4","Accuracy - Corrupted Images":"32.4"},"uses_additional_data":false,"paper_date":"2020-07-01","paper":"/paper/measuring-robustness-to-natural-distribution","paper_url":"https://arxiv.org/abs/2007.00644v2","paper_title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","code":"https://github.com/modestyachts/imagenet-testbed","n_code_links":1,"syntology":null},{"rank_in_archive_order":51,"model":"EfficientNet-B2","metrics":{"Accuracy - All Images":"38.1","Accuracy - Clean Images":"42.8","Accuracy - Corrupted Images":"31.4"},"uses_additional_data":false,"paper_date":"2019-05-28","paper":"/paper/efficientnet-rethinking-model-scaling-for","paper_url":"https://arxiv.org/abs/1905.11946v5","paper_title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","code":"https://github.com/ultralytics/yolov5","n_code_links":144,"syntology":{"n_ran":171,"n_unverified":131,"n_samples":302,"n_pointer_only_licence":112}},{"rank_in_archive_order":52,"model":"ResNet-50 (IN-C_pixelate)","metrics":{"Accuracy - All Images":"37.4","Accuracy - Clean Images":"41.4","Accuracy - Corrupted Images":"30.9"},"uses_additional_data":false,"paper_date":"2020-07-01","paper":"/paper/measuring-robustness-to-natural-distribution","paper_url":"https://arxiv.org/abs/2007.00644v2","paper_title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","code":"https://github.com/modestyachts/imagenet-testbed","n_code_links":1,"syntology":null},{"rank_in_archive_order":53,"model":"VGG-16 BN (lpf2)","metrics":{"Accuracy - All Images":"37.2","Accuracy - Clean Images":"41.8","Accuracy - Corrupted Images":"31.3"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":54,"model":"ResNet-34 (lpf5)","metrics":{"Accuracy - All Images":"37.2","Accuracy - Clean Images":"42.5","Accuracy - Corrupted Images":"29.9"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":55,"model":"VGG-16 BN (lpf5)","metrics":{"Accuracy - All Images":"37","Accuracy - Clean Images":"41.7","Accuracy - Corrupted Images":"30.8"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":56,"model":"VGG-16 BN (lpf3)","metrics":{"Accuracy - All Images":"36.9","Accuracy - Clean Images":"42.1","Accuracy - Corrupted Images":"30.6"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":57,"model":"VGG-16 BN","metrics":{"Accuracy - All Images":"36.7","Accuracy - Clean Images":"41.1","Accuracy - Corrupted Images":"31.1"},"uses_additional_data":false,"paper_date":"2014-09-04","paper":"/paper/very-deep-convolutional-networks-for-large","paper_url":"http://arxiv.org/abs/1409.1556v6","paper_title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","code":"https://github.com/tensorflow/models/tree/master/research/slim","n_code_links":305,"syntology":{"n_ran":12,"n_unverified":110,"n_samples":122,"n_pointer_only_licence":4}},{"rank_in_archive_order":58,"model":"EfficientNet-B1","metrics":{"Accuracy - All Images":"36.7","Accuracy - Clean Images":"41.5","Accuracy - Corrupted Images":"30.9"},"uses_additional_data":false,"paper_date":"2019-05-28","paper":"/paper/efficientnet-rethinking-model-scaling-for","paper_url":"https://arxiv.org/abs/1905.11946v5","paper_title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","code":"https://github.com/ultralytics/yolov5","n_code_links":144,"syntology":{"n_ran":171,"n_unverified":131,"n_samples":302,"n_pointer_only_licence":112}},{"rank_in_archive_order":59,"model":"ResNet-50 (IN-C_contrast)","metrics":{"Accuracy - All Images":"36.5","Accuracy - Clean Images":"40.9","Accuracy - Corrupted Images":"30.7"},"uses_additional_data":false,"paper_date":"2020-07-01","paper":"/paper/measuring-robustness-to-natural-distribution","paper_url":"https://arxiv.org/abs/2007.00644v2","paper_title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","code":"https://github.com/modestyachts/imagenet-testbed","n_code_links":1,"syntology":null},{"rank_in_archive_order":60,"model":"ResNet-50 (IN-C_jpeg_compression)","metrics":{"Accuracy - All Images":"36.5","Accuracy - Clean Images":"41.3","Accuracy - Corrupted Images":"30.3"},"uses_additional_data":false,"paper_date":"2020-07-01","paper":"/paper/measuring-robustness-to-natural-distribution","paper_url":"https://arxiv.org/abs/2007.00644v2","paper_title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","code":"https://github.com/modestyachts/imagenet-testbed","n_code_links":1,"syntology":null},{"rank_in_archive_order":61,"model":"ResNet-50 (IN-C_gaussian_noise)","metrics":{"Accuracy - All Images":"36.4","Accuracy - Clean Images":"40.6","Accuracy - Corrupted Images":"30.2"},"uses_additional_data":false,"paper_date":"2020-07-01","paper":"/paper/measuring-robustness-to-natural-distribution","paper_url":"https://arxiv.org/abs/2007.00644v2","paper_title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","code":"https://github.com/modestyachts/imagenet-testbed","n_code_links":1,"syntology":null},{"rank_in_archive_order":62,"model":"VGG-19 BN","metrics":{"Accuracy - All Images":"36.2","Accuracy - Clean Images":"40.8","Accuracy - Corrupted Images":"29.4"},"uses_additional_data":false,"paper_date":"2014-09-04","paper":"/paper/very-deep-convolutional-networks-for-large","paper_url":"http://arxiv.org/abs/1409.1556v6","paper_title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","code":"https://github.com/tensorflow/models/tree/master/research/slim","n_code_links":305,"syntology":{"n_ran":12,"n_unverified":110,"n_samples":122,"n_pointer_only_licence":4}},{"rank_in_archive_order":63,"model":"ResNet-50 (IN-C_frost)","metrics":{"Accuracy - All Images":"36.1","Accuracy - Clean Images":"40","Accuracy - Corrupted Images":"29.7"},"uses_additional_data":false,"paper_date":"2020-07-01","paper":"/paper/measuring-robustness-to-natural-distribution","paper_url":"https://arxiv.org/abs/2007.00644v2","paper_title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","code":"https://github.com/modestyachts/imagenet-testbed","n_code_links":1,"syntology":null},{"rank_in_archive_order":64,"model":"MobileNetV2 (lpf3)","metrics":{"Accuracy - All Images":"36","Accuracy - Clean Images":"40.3","Accuracy - Corrupted Images":"30.4"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":65,"model":"ResNet-50 (IN-C_fog_aws)","metrics":{"Accuracy - All Images":"35.9","Accuracy - Clean Images":"39.9","Accuracy - Corrupted Images":"30.3"},"uses_additional_data":false,"paper_date":"2020-07-01","paper":"/paper/measuring-robustness-to-natural-distribution","paper_url":"https://arxiv.org/abs/2007.00644v2","paper_title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","code":"https://github.com/modestyachts/imagenet-testbed","n_code_links":1,"syntology":null},{"rank_in_archive_order":66,"model":"MobileNetV2 (lpf5)","metrics":{"Accuracy - All Images":"35.8","Accuracy - Clean Images":"40.1","Accuracy - Corrupted Images":"29.1"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":67,"model":"ResNet-50 (IN-C_motion_blur)","metrics":{"Accuracy - All Images":"35.7","Accuracy - Clean Images":"39.6","Accuracy - Corrupted Images":"30.2"},"uses_additional_data":false,"paper_date":"2020-07-01","paper":"/paper/measuring-robustness-to-natural-distribution","paper_url":"https://arxiv.org/abs/2007.00644v2","paper_title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","code":"https://github.com/modestyachts/imagenet-testbed","n_code_links":1,"syntology":null},{"rank_in_archive_order":68,"model":"ResNet-18 (lpf3)","metrics":{"Accuracy - All Images":"35.6","Accuracy - Clean Images":"39.5","Accuracy - Corrupted Images":"28.5"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":69,"model":"MobileNetV2 (lpf2)","metrics":{"Accuracy - All Images":"35.5","Accuracy - Clean Images":"39.2","Accuracy - Corrupted Images":"30.3"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":70,"model":"ResNet-18 (lpf2)","metrics":{"Accuracy - All Images":"35.5","Accuracy - Clean Images":"40.1","Accuracy - Corrupted Images":"28.7"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":71,"model":"VGG-16 (lpf3)","metrics":{"Accuracy - All Images":"35.1","Accuracy - Clean Images":"40","Accuracy - Corrupted Images":"28.2"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":72,"model":"EfficientNet-B0 (autoaug)","metrics":{"Accuracy - All Images":"34.9","Accuracy - Clean Images":"40.1","Accuracy - Corrupted Images":"27.3"},"uses_additional_data":false,"paper_date":"2018-05-24","paper":"/paper/autoaugment-learning-augmentation-policies","paper_url":"http://arxiv.org/abs/1805.09501v3","paper_title":"AutoAugment: Learning Augmentation Policies from Data","code":"https://github.com/tensorflow/models/tree/master/research/autoaugment","n_code_links":33,"syntology":{"n_ran":6,"n_unverified":37,"n_samples":43,"n_pointer_only_licence":2}},{"rank_in_archive_order":73,"model":"VGG-19","metrics":{"Accuracy - All Images":"34.7","Accuracy - Clean Images":"39.3","Accuracy - Corrupted Images":"29"},"uses_additional_data":false,"paper_date":"2014-09-04","paper":"/paper/very-deep-convolutional-networks-for-large","paper_url":"http://arxiv.org/abs/1409.1556v6","paper_title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","code":"https://github.com/tensorflow/models/tree/master/research/slim","n_code_links":305,"syntology":{"n_ran":12,"n_unverified":110,"n_samples":122,"n_pointer_only_licence":4}},{"rank_in_archive_order":74,"model":"VGG-16","metrics":{"Accuracy - All Images":"34.7","Accuracy - Clean Images":"39.5","Accuracy - Corrupted Images":"28.5"},"uses_additional_data":false,"paper_date":"2014-09-04","paper":"/paper/very-deep-convolutional-networks-for-large","paper_url":"http://arxiv.org/abs/1409.1556v6","paper_title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","code":"https://github.com/tensorflow/models/tree/master/research/slim","n_code_links":305,"syntology":{"n_ran":12,"n_unverified":110,"n_samples":122,"n_pointer_only_licence":4}},{"rank_in_archive_order":75,"model":"ResNet-18 (lpf5)","metrics":{"Accuracy - All Images":"34.7","Accuracy - Clean Images":"38.9","Accuracy - Corrupted Images":"27.7"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":76,"model":"VGG-16 (lpf5)","metrics":{"Accuracy - All Images":"34.5","Accuracy - Clean Images":"39.4","Accuracy - Corrupted Images":"27.8"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":77,"model":"EfficientNet-B0","metrics":{"Accuracy - All Images":"34.2","Accuracy - Clean Images":"38.4","Accuracy - Corrupted Images":"27.4"},"uses_additional_data":false,"paper_date":"2019-05-28","paper":"/paper/efficientnet-rethinking-model-scaling-for","paper_url":"https://arxiv.org/abs/1905.11946v5","paper_title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","code":"https://github.com/ultralytics/yolov5","n_code_links":144,"syntology":{"n_ran":171,"n_unverified":131,"n_samples":302,"n_pointer_only_licence":112}},{"rank_in_archive_order":78,"model":"VGG-13 BN","metrics":{"Accuracy - All Images":"33.7","Accuracy - Clean Images":"38.4","Accuracy - Corrupted Images":"28.3"},"uses_additional_data":false,"paper_date":"2014-09-04","paper":"/paper/very-deep-convolutional-networks-for-large","paper_url":"http://arxiv.org/abs/1409.1556v6","paper_title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","code":"https://github.com/tensorflow/models/tree/master/research/slim","n_code_links":305,"syntology":{"n_ran":12,"n_unverified":110,"n_samples":122,"n_pointer_only_licence":4}},{"rank_in_archive_order":79,"model":"VGG-16 (lpf2)","metrics":{"Accuracy - All Images":"33.5","Accuracy - Clean Images":"38.5","Accuracy - Corrupted Images":"26.7"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":80,"model":"VGG-11 BN","metrics":{"Accuracy - All Images":"32.9","Accuracy - Clean Images":"37.1","Accuracy - Corrupted Images":"25.8"},"uses_additional_data":false,"paper_date":"2014-09-04","paper":"/paper/very-deep-convolutional-networks-for-large","paper_url":"http://arxiv.org/abs/1409.1556v6","paper_title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","code":"https://github.com/tensorflow/models/tree/master/research/slim","n_code_links":305,"syntology":{"n_ran":12,"n_unverified":110,"n_samples":122,"n_pointer_only_licence":4}},{"rank_in_archive_order":81,"model":"ResNet-50 (IN-C_zoom_blur)","metrics":{"Accuracy - All Images":"32.7","Accuracy - Clean Images":"36.6","Accuracy - Corrupted Images":"28.3"},"uses_additional_data":false,"paper_date":"2020-07-01","paper":"/paper/measuring-robustness-to-natural-distribution","paper_url":"https://arxiv.org/abs/2007.00644v2","paper_title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","code":"https://github.com/modestyachts/imagenet-testbed","n_code_links":1,"syntology":null},{"rank_in_archive_order":82,"model":"VGG-13","metrics":{"Accuracy - All Images":"32.4","Accuracy - Clean Images":"36.5","Accuracy - Corrupted Images":"26.4"},"uses_additional_data":false,"paper_date":"2014-09-04","paper":"/paper/very-deep-convolutional-networks-for-large","paper_url":"http://arxiv.org/abs/1409.1556v6","paper_title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","code":"https://github.com/tensorflow/models/tree/master/research/slim","n_code_links":305,"syntology":{"n_ran":12,"n_unverified":110,"n_samples":122,"n_pointer_only_licence":4}},{"rank_in_archive_order":83,"model":"VGG-11","metrics":{"Accuracy - All Images":"31.5","Accuracy - Clean Images":"36.1","Accuracy - Corrupted Images":"25.2"},"uses_additional_data":false,"paper_date":"2014-09-04","paper":"/paper/very-deep-convolutional-networks-for-large","paper_url":"http://arxiv.org/abs/1409.1556v6","paper_title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","code":"https://github.com/tensorflow/models/tree/master/research/slim","n_code_links":305,"syntology":{"n_ran":12,"n_unverified":110,"n_samples":122,"n_pointer_only_licence":4}},{"rank_in_archive_order":84,"model":"ResNet-50 (IN-C_greyscale)","metrics":{"Accuracy - All Images":"30.2","Accuracy - Clean Images":"34.3","Accuracy - Corrupted Images":"24.3"},"uses_additional_data":false,"paper_date":"2020-07-01","paper":"/paper/measuring-robustness-to-natural-distribution","paper_url":"https://arxiv.org/abs/2007.00644v2","paper_title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","code":"https://github.com/modestyachts/imagenet-testbed","n_code_links":1,"syntology":null},{"rank_in_archive_order":85,"model":"ResNet-50 (adv-train-free)","metrics":{"Accuracy - All Images":"26.7","Accuracy - Clean Images":"30.9","Accuracy - Corrupted Images":"20.5"},"uses_additional_data":false,"paper_date":"2019-04-29","paper":"/paper/adversarial-training-for-free","paper_url":"https://arxiv.org/abs/1904.12843v2","paper_title":"Adversarial Training for Free!","code":"https://github.com/locuslab/fast_adversarial","n_code_links":6,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":86,"model":"ResNet-50 (SIN)","metrics":{"Accuracy - All Images":"25.3","Accuracy - Clean Images":"30","Accuracy - Corrupted Images":"20.4"},"uses_additional_data":false,"paper_date":"2018-11-29","paper":"/paper/imagenet-trained-cnns-are-biased-towards","paper_url":"https://arxiv.org/abs/1811.12231v3","paper_title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","code":"https://github.com/rgeirhos/texture-vs-shape","n_code_links":7,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":87,"model":"AlexNet (lpf3)","metrics":{"Accuracy - All Images":"23.1","Accuracy - Clean Images":"26.8","Accuracy - Corrupted Images":"17.5"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":88,"model":"AlexNet (lpf2)","metrics":{"Accuracy - All Images":"22.8","Accuracy - Clean Images":"26.8","Accuracy - Corrupted Images":"18.2"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":89,"model":"AlexNet (lpf5)","metrics":{"Accuracy - All Images":"22.7","Accuracy - Clean Images":"26.8","Accuracy - Corrupted Images":"18.4"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/190411486","paper_url":"https://arxiv.org/abs/1904.11486v2","paper_title":"Making Convolutional Networks Shift-Invariant Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":90,"model":"ViT-8/B-224","metrics":{"Accuracy - Clean Images":"450"},"uses_additional_data":true,"paper_date":"2020-10-22","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","paper_url":"https://arxiv.org/abs/2010.11929v2","paper_title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","code":"https://github.com/huggingface/transformers","n_code_links":158,"syntology":{"n_ran":281,"n_unverified":138,"n_samples":419,"n_pointer_only_licence":154}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,795 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":73,"rows_with_any_sample_ran":69,"distinct_papers_with_graph_line":17,"distinct_papers_with_any_sample_ran":15,"samples_over_distinct_papers":{"n_ran":912,"n_unverified":678,"n_samples":1590,"n_pointer_only_licence":534,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":2749,"n_unverified":2718,"n_samples":5467,"n_pointer_only_licence":1751,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}