{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/circumventing-outliers-of-autoaugment-with","title":"Circumventing Outliers of AutoAugment with Knowledge Distillation","arxiv_id":"2003.11342","date":"2020-03-25","proceeding":"ECCV 2020 8","authors":["Longhui Wei","An Xiao","Lingxi Xie","Xin Chen","Xiaopeng Zhang","Qi Tian"],"abstract":"AutoAugment has been a powerful algorithm that improves the accuracy of many vision tasks, yet it is sensitive to the operator space as well as hyper-parameters, and an improper setting may degenerate network optimization. This paper delves deep into the working mechanism, and reveals that AutoAugment may remove part of discriminative information from the training image and so insisting on the ground-truth label is no longer the best option. To relieve the inaccuracy of supervision, we make use of knowledge distillation that refers to the output of a teacher model to guide network training. Experiments are performed in standard image classification benchmarks, and demonstrate the effectiveness of our approach in suppressing noise of data augmentation and stabilizing training. Upon the cooperation of knowledge distillation and AutoAugment, we claim the new state-of-the-art on ImageNet classification with a top-1 accuracy of 85.8%.","url_abs":"https://arxiv.org/abs/2003.11342v1","url_pdf":"https://arxiv.org/pdf/2003.11342v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"circumventing-outliers-of-autoaugment-with","repo_url":"https://github.com/chenyang4/resmooth","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"autoaugment","method_name":"AutoAugment"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"efficientnet","method_name":"EfficientNet"},{"method_slug":"fixres","method_name":"FixRes"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"randaugment","method_name":"RandAugment"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"shakedrop","method_name":"ShakeDrop"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"squeeze-and-excitation-block","method_name":"Squeeze-and-Excitation Block"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"KDforAA (EfficientNet-B8)","rank_in_archive_order":195,"of":1060,"metrics":{"Number of params":"88M","Top 1 Accuracy":"85.8%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"KDforAA (EfficientNet-B7)","rank_in_archive_order":222,"of":1060,"metrics":{"Number of params":"66M","Top 1 Accuracy":"85.5%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2003.11342","atlas_url":"https://app.syntology.ai/?focus=2003.11342","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}