{"url":"/sota/semantic-segmentation-on-pascal-voc-2012","task":{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","note":null},"dataset":{"name":"PASCAL VOC 2012 test","url":"/dataset/pascal-voc-2012-test"},"category":"Computer Vision","categories":["Computer Code","Computer Vision","Medical","Robots"],"category_note":null,"description":null,"description_from":null,"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":["Mean IoU","FLOPS","Params"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Mean IoU":"higher","FLOPS":"lower","Params":"lower"}},"counts":{"rows":51,"rows_with_code":45,"rows_with_paper_page":51,"rows_dated":51,"rows_using_additional_data":7},"rows":[{"rank_in_archive_order":1,"model":"DeepLabv3+ (Xception-65-JFT)","metrics":{"Mean IoU":"89.0%"},"uses_additional_data":true,"paper_date":"2018-02-07","paper":"/paper/encoder-decoder-with-atrous-separable","paper_url":"http://arxiv.org/abs/1802.02611v3","paper_title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","code":"https://github.com/tensorflow/models/tree/master/research/deeplab","n_code_links":78,"syntology":{"n_ran":43,"n_unverified":29,"n_samples":72,"n_pointer_only_licence":40}},{"rank_in_archive_order":2,"model":"DeepLabv3+ (Xception-JFT)","metrics":{"Mean IoU":"89.0%"},"uses_additional_data":true,"paper_date":"2018-02-07","paper":"/paper/encoder-decoder-with-atrous-separable","paper_url":"http://arxiv.org/abs/1802.02611v3","paper_title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","code":"https://github.com/tensorflow/models/tree/master/research/deeplab","n_code_links":78,"syntology":{"n_ran":43,"n_unverified":29,"n_samples":72,"n_pointer_only_licence":40}},{"rank_in_archive_order":3,"model":"DeepLabv3-JFT","metrics":{"Mean IoU":"86.9%"},"uses_additional_data":true,"paper_date":"2017-06-17","paper":"/paper/rethinking-atrous-convolution-for-semantic","paper_url":"http://arxiv.org/abs/1706.05587v3","paper_title":"Rethinking Atrous Convolution for Semantic Image Segmentation","code":"https://github.com/tensorflow/models","n_code_links":77,"syntology":{"n_ran":3,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":3}},{"rank_in_archive_order":4,"model":"CASIA_IVA_SDN","metrics":{"Mean IoU":"86.6%"},"uses_additional_data":false,"paper_date":"2017-08-16","paper":"/paper/stacked-deconvolutional-network-for-semantic","paper_url":"http://arxiv.org/abs/1708.04943v1","paper_title":"Stacked Deconvolutional Network for Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"Smooth Network with Channel Attention Block","metrics":{"Mean IoU":"86.2%"},"uses_additional_data":false,"paper_date":"2018-04-25","paper":"/paper/learning-a-discriminative-feature-network-for","paper_url":"http://arxiv.org/abs/1804.09337v1","paper_title":"Learning a Discriminative Feature Network for Semantic Segmentation","code":"https://github.com/ycszen/TorchSeg","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":8,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"SANet (pretraining on COCO dataset)","metrics":{"Mean IoU":"86.1%"},"uses_additional_data":false,"paper_date":"2019-09-08","paper":"/paper/squeeze-and-attention-networks-for-semantic","paper_url":"https://arxiv.org/abs/1909.03402v4","paper_title":"Squeeze-and-Attention Networks for Semantic Segmentation","code":"https://github.com/its-mayank/SqueezeAttention-PyTorch","n_code_links":4,"syntology":null},{"rank_in_archive_order":7,"model":"EncNet","metrics":{"Mean IoU":"85.9%"},"uses_additional_data":false,"paper_date":"2018-03-23","paper":"/paper/context-encoding-for-semantic-segmentation","paper_url":"http://arxiv.org/abs/1803.08904v1","paper_title":"Context Encoding for Semantic Segmentation","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":12,"syntology":{"n_ran":1,"n_unverified":7,"n_samples":8,"n_pointer_only_licence":7}},{"rank_in_archive_order":8,"model":"HamNet w/o COCO (ResNet-101)","metrics":{"Mean IoU":"85.9%"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/is-attention-better-than-matrix-decomposition-1","paper_url":"https://arxiv.org/abs/2109.04553v2","paper_title":"Is Attention Better Than Matrix Decomposition?","code":"https://github.com/Gsunshine/Enjoy-Hamburger","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":9,"model":"Auto-DeepLab-L","metrics":{"Mean IoU":"85.6%"},"uses_additional_data":false,"paper_date":"2019-01-10","paper":"/paper/auto-deeplab-hierarchical-neural-architecture","paper_url":"http://arxiv.org/abs/1901.02985v2","paper_title":"Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation","code":"https://github.com/tensorflow/models","n_code_links":12,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":10,"model":"PSPNet","metrics":{"Mean IoU":"85.4%"},"uses_additional_data":true,"paper_date":"2016-12-04","paper":"/paper/pyramid-scene-parsing-network","paper_url":"http://arxiv.org/abs/1612.01105v2","paper_title":"Pyramid Scene Parsing Network","code":"https://github.com/tensorflow/models","n_code_links":67,"syntology":{"n_ran":7,"n_unverified":22,"n_samples":29,"n_pointer_only_licence":5}},{"rank_in_archive_order":11,"model":"ResNet-38 MS COCO","metrics":{"Mean IoU":"84.9%"},"uses_additional_data":false,"paper_date":"2016-11-30","paper":"/paper/wider-or-deeper-revisiting-the-resnet-model","paper_url":"http://arxiv.org/abs/1611.10080v1","paper_title":"Wider or Deeper: Revisiting the ResNet Model for Visual Recognition","code":"https://github.com/itijyou/ademxapp","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":12,"model":"OCR (HRNetV2-W48)","metrics":{"Mean IoU":"84.5%"},"uses_additional_data":false,"paper_date":"2019-09-24","paper":"/paper/object-contextual-representations-for","paper_url":"https://arxiv.org/abs/1909.11065v6","paper_title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":11,"syntology":{"n_ran":4,"n_unverified":5,"n_samples":9,"n_pointer_only_licence":1}},{"rank_in_archive_order":13,"model":"OCR (ResNet-101)","metrics":{"Mean IoU":"84.3%"},"uses_additional_data":false,"paper_date":"2019-09-24","paper":"/paper/object-contextual-representations-for","paper_url":"https://arxiv.org/abs/1909.11065v6","paper_title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":11,"syntology":{"n_ran":4,"n_unverified":5,"n_samples":9,"n_pointer_only_licence":1}},{"rank_in_archive_order":14,"model":"Multipath-RefineNet","metrics":{"Mean IoU":"84.2%"},"uses_additional_data":false,"paper_date":"2016-11-20","paper":"/paper/refinenet-multi-path-refinement-networks-for","paper_url":"http://arxiv.org/abs/1611.06612v3","paper_title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","code":"https://github.com/guosheng/refinenet","n_code_links":13,"syntology":{"n_ran":1,"n_unverified":6,"n_samples":7,"n_pointer_only_licence":1}},{"rank_in_archive_order":15,"model":"ShelfNet","metrics":{"Mean IoU":"84.2%"},"uses_additional_data":false,"paper_date":"2018-11-27","paper":"/paper/multi-path-segmentation-network","paper_url":"https://arxiv.org/abs/1811.11254v6","paper_title":"ShelfNet for Fast Semantic Segmentation","code":"https://github.com/Deci-AI/super-gradients","n_code_links":6,"syntology":null},{"rank_in_archive_order":16,"model":"EANet (ResNet-101)","metrics":{"Mean IoU":"84%"},"uses_additional_data":false,"paper_date":"2021-05-05","paper":"/paper/beyond-self-attention-external-attention","paper_url":"https://arxiv.org/abs/2105.02358v2","paper_title":"Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks","code":"https://github.com/xmu-xiaoma666/External-Attention-pytorch","n_code_links":7,"syntology":null},{"rank_in_archive_order":17,"model":"Large Kernel Matters","metrics":{"Mean IoU":"83.6%"},"uses_additional_data":false,"paper_date":"2017-03-08","paper":"/paper/large-kernel-matters-improve-semantic","paper_url":"http://arxiv.org/abs/1703.02719v1","paper_title":"Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network","code":"https://github.com/y-ouali/pytorch_segmentation","n_code_links":2,"syntology":null},{"rank_in_archive_order":18,"model":"TripleNet","metrics":{"Mean IoU":"83.3%"},"uses_additional_data":false,"paper_date":"2018-09-25","paper":"/paper/triply-supervised-decoder-networks-for-joint","paper_url":"http://arxiv.org/abs/1809.09299v1","paper_title":"Triply Supervised Decoder Networks for Joint Detection and Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"SANet","metrics":{"Mean IoU":"83.2%"},"uses_additional_data":false,"paper_date":"2019-09-08","paper":"/paper/squeeze-and-attention-networks-for-semantic","paper_url":"https://arxiv.org/abs/1909.03402v4","paper_title":"Squeeze-and-Attention Networks for Semantic Segmentation","code":"https://github.com/its-mayank/SqueezeAttention-PyTorch","n_code_links":4,"syntology":null},{"rank_in_archive_order":20,"model":"TuSimple","metrics":{"Mean IoU":"83.1%"},"uses_additional_data":false,"paper_date":"2017-02-27","paper":"/paper/understanding-convolution-for-semantic","paper_url":"http://arxiv.org/abs/1702.08502v3","paper_title":"Understanding Convolution for Semantic Segmentation","code":"https://github.com/y-ouali/pytorch_segmentation","n_code_links":5,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"EncNet (ResNet-101)","metrics":{"Mean IoU":"82.9%"},"uses_additional_data":false,"paper_date":"2018-03-23","paper":"/paper/context-encoding-for-semantic-segmentation","paper_url":"http://arxiv.org/abs/1803.08904v1","paper_title":"Context Encoding for Semantic Segmentation","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":12,"syntology":{"n_ran":1,"n_unverified":7,"n_samples":8,"n_pointer_only_licence":7}},{"rank_in_archive_order":22,"model":"DFN (ResNet-101)","metrics":{"Mean IoU":"82.7%"},"uses_additional_data":false,"paper_date":"2018-04-25","paper":"/paper/learning-a-discriminative-feature-network-for","paper_url":"http://arxiv.org/abs/1804.09337v1","paper_title":"Learning a Discriminative Feature Network for Semantic Segmentation","code":"https://github.com/ycszen/TorchSeg","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":8,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":23,"model":"Deep Layer Cascade (LC)","metrics":{"Mean IoU":"82.7%"},"uses_additional_data":false,"paper_date":"2017-04-05","paper":"/paper/not-all-pixels-are-equal-difficulty-aware","paper_url":"http://arxiv.org/abs/1704.01344v1","paper_title":"Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade","code":"https://github.com/liuziwei7/region-conv","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"Light-Weight-RefineNet-152","metrics":{"Mean IoU":"82.7%"},"uses_additional_data":false,"paper_date":"2018-10-08","paper":"/paper/light-weight-refinenet-for-real-time-semantic","paper_url":"http://arxiv.org/abs/1810.03272v1","paper_title":"Light-Weight RefineNet for Real-Time Semantic Segmentation","code":"https://github.com/DrSleep/light-weight-refinenet","n_code_links":2,"syntology":null},{"rank_in_archive_order":25,"model":"DANet (ResNet-101)","metrics":{"Mean IoU":"82.6%"},"uses_additional_data":false,"paper_date":"2018-09-09","paper":"/paper/dual-attention-network-for-scene-segmentation","paper_url":"http://arxiv.org/abs/1809.02983v4","paper_title":"Dual Attention Network for Scene Segmentation","code":"https://github.com/xmu-xiaoma666/External-Attention-pytorch","n_code_links":12,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":5}},{"rank_in_archive_order":26,"model":"PSPNet (ResNet-101)","metrics":{"Mean IoU":"82.6%"},"uses_additional_data":false,"paper_date":"2016-12-04","paper":"/paper/pyramid-scene-parsing-network","paper_url":"http://arxiv.org/abs/1612.01105v2","paper_title":"Pyramid Scene Parsing Network","code":"https://github.com/tensorflow/models","n_code_links":67,"syntology":{"n_ran":7,"n_unverified":22,"n_samples":29,"n_pointer_only_licence":5}},{"rank_in_archive_order":27,"model":"Light-Weight-RefineNet-101","metrics":{"Mean IoU":"82.0%"},"uses_additional_data":false,"paper_date":"2018-10-08","paper":"/paper/light-weight-refinenet-for-real-time-semantic","paper_url":"http://arxiv.org/abs/1810.03272v1","paper_title":"Light-Weight RefineNet for Real-Time Semantic Segmentation","code":"https://github.com/DrSleep/light-weight-refinenet","n_code_links":2,"syntology":null},{"rank_in_archive_order":28,"model":"Light-Weight-RefineNet-50","metrics":{"Mean IoU":"81.1%"},"uses_additional_data":false,"paper_date":"2018-10-08","paper":"/paper/light-weight-refinenet-for-real-time-semantic","paper_url":"http://arxiv.org/abs/1810.03272v1","paper_title":"Light-Weight RefineNet for Real-Time Semantic Segmentation","code":"https://github.com/DrSleep/light-weight-refinenet","n_code_links":2,"syntology":null},{"rank_in_archive_order":29,"model":"CentraleSupelec Deep G-CRF","metrics":{"Mean IoU":"80.2%"},"uses_additional_data":false,"paper_date":"2016-03-28","paper":"/paper/fast-exact-and-multi-scale-inference-for","paper_url":"http://arxiv.org/abs/1603.08358v4","paper_title":"Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs","code":"https://github.com/siddharthachandra/gcrf","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"EdgeNeXt","metrics":{"FLOPS":"8.7G","Mean IoU":"80.2%","Params":"6.5M"},"uses_additional_data":false,"paper_date":"2022-06-21","paper":"/paper/edgenext-efficiently-amalgamated-cnn","paper_url":"https://arxiv.org/abs/2206.10589v3","paper_title":"EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":8,"syntology":{"n_ran":1,"n_unverified":9,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":31,"model":"DeepLab-CRF (ResNet-101)","metrics":{"Mean IoU":"79.7%"},"uses_additional_data":true,"paper_date":"2016-06-02","paper":"/paper/deeplab-semantic-image-segmentation-with-deep","paper_url":"http://arxiv.org/abs/1606.00915v2","paper_title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","code":"https://github.com/tensorflow/models/tree/master/research/deeplab","n_code_links":47,"syntology":{"n_ran":28,"n_unverified":35,"n_samples":63,"n_pointer_only_licence":16}},{"rank_in_archive_order":32,"model":"WASPnet-CRF (ours)","metrics":{"Mean IoU":"79.6%"},"uses_additional_data":false,"paper_date":"2019-12-06","paper":"/paper/waterfall-atrous-spatial-pooling-architecture","paper_url":"https://arxiv.org/abs/1912.03183v1","paper_title":"Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation","code":"https://github.com/bmartacho/WASP","n_code_links":1,"syntology":null},{"rank_in_archive_order":33,"model":"Light-Weight-RefineNet-MobileNet-v2","metrics":{"Mean IoU":"79.2%"},"uses_additional_data":false,"paper_date":"2018-10-08","paper":"/paper/light-weight-refinenet-for-real-time-semantic","paper_url":"http://arxiv.org/abs/1810.03272v1","paper_title":"Light-Weight RefineNet for Real-Time Semantic Segmentation","code":"https://github.com/DrSleep/light-weight-refinenet","n_code_links":2,"syntology":null},{"rank_in_archive_order":34,"model":"Deeplab-v2 with Lovasz-Softmax loss","metrics":{"Mean IoU":"79.00%"},"uses_additional_data":true,"paper_date":"2017-05-24","paper":"/paper/the-lovasz-softmax-loss-a-tractable-surrogate","paper_url":"http://arxiv.org/abs/1705.08790v2","paper_title":"The Lovász-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks","code":"https://github.com/CoinCheung/pytorch-loss","n_code_links":4,"syntology":null},{"rank_in_archive_order":35,"model":"Deeplab-v2 + Lovász-Softmax","metrics":{"Mean IoU":"79.0%"},"uses_additional_data":false,"paper_date":"2017-05-24","paper":"/paper/the-lovasz-softmax-loss-a-tractable-surrogate","paper_url":"http://arxiv.org/abs/1705.08790v2","paper_title":"The Lovász-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks","code":"https://github.com/CoinCheung/pytorch-loss","n_code_links":4,"syntology":null},{"rank_in_archive_order":36,"model":"CRF-RNN","metrics":{"Mean IoU":"74.7%"},"uses_additional_data":false,"paper_date":"2015-02-11","paper":"/paper/conditional-random-fields-as-recurrent-neural-1","paper_url":"http://arxiv.org/abs/1502.03240v3","paper_title":"Conditional Random Fields as Recurrent Neural Networks","code":"https://github.com/torrvision/crfasrnn","n_code_links":6,"syntology":{"n_ran":1,"n_unverified":7,"n_samples":8,"n_pointer_only_licence":2}},{"rank_in_archive_order":37,"model":"SID","metrics":{"Mean IoU":"72.8%"},"uses_additional_data":false,"paper_date":"2016-03-24","paper":"/paper/simple-does-it-weakly-supervised-instance-and","paper_url":"http://arxiv.org/abs/1603.07485v2","paper_title":"Simple Does It: Weakly Supervised Instance and Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":38,"model":"DeepLab-MSc-CRF-LargeFOV (VGG-16)","metrics":{"Mean IoU":"71.6%"},"uses_additional_data":false,"paper_date":"2014-12-22","paper":"/paper/semantic-image-segmentation-with-deep","paper_url":"http://arxiv.org/abs/1412.7062v4","paper_title":"Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs","code":"https://github.com/tensorflow/models","n_code_links":18,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":39,"model":"ParseNet","metrics":{"Mean IoU":"69.8%"},"uses_additional_data":false,"paper_date":"2015-06-15","paper":"/paper/parsenet-looking-wider-to-see-better","paper_url":"http://arxiv.org/abs/1506.04579v2","paper_title":"ParseNet: Looking Wider to See Better","code":"https://github.com/tensorflow/models/tree/master/research/deeplab","n_code_links":4,"syntology":null},{"rank_in_archive_order":40,"model":"Dilated FCN-2s VGG19","metrics":{"Mean IoU":"69%"},"uses_additional_data":false,"paper_date":"2017-07-26","paper":"/paper/efficient-yet-deep-convolutional-neural","paper_url":"http://arxiv.org/abs/1707.08254v3","paper_title":"Efficient Yet Deep Convolutional Neural Networks for Semantic Segmentation","code":"https://github.com/SharifAmit/DilatedFCNSegmentation","n_code_links":1,"syntology":null},{"rank_in_archive_order":41,"model":"ESPNetv2","metrics":{"Mean IoU":"68.0%"},"uses_additional_data":false,"paper_date":"2018-11-28","paper":"/paper/espnetv2-a-light-weight-power-efficient-and","paper_url":"http://arxiv.org/abs/1811.11431v3","paper_title":"ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":10,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":42,"model":"Dilated Convolutions","metrics":{"Mean IoU":"67.6%"},"uses_additional_data":false,"paper_date":"2015-11-23","paper":"/paper/multi-scale-context-aggregation-by-dilated","paper_url":"http://arxiv.org/abs/1511.07122v3","paper_title":"Multi-Scale Context Aggregation by Dilated Convolutions","code":"https://github.com/fyu/dilation","n_code_links":9,"syntology":{"n_ran":2,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":2}},{"rank_in_archive_order":43,"model":"DiCENet","metrics":{"Mean IoU":"67.31%"},"uses_additional_data":false,"paper_date":"2019-06-08","paper":"/paper/dicenet-dimension-wise-convolutions-for","paper_url":"https://arxiv.org/abs/1906.03516v3","paper_title":"DiCENet: Dimension-wise Convolutions for Efficient Networks","code":"https://github.com/osmr/imgclsmob","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":44,"model":"RRM","metrics":{"Mean IoU":"66.5"},"uses_additional_data":false,"paper_date":"2019-11-19","paper":"/paper/reliability-does-matter-an-end-to-end-weakly","paper_url":"https://arxiv.org/abs/1911.08039v1","paper_title":"Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach","code":"https://github.com/zbf1991/RRM","n_code_links":1,"syntology":null},{"rank_in_archive_order":45,"model":"SSDD","metrics":{"Mean IoU":"65.5"},"uses_additional_data":false,"paper_date":"2019-11-04","paper":"/paper/self-supervised-difference-detection-for-1","paper_url":"https://arxiv.org/abs/1911.01370v2","paper_title":"Self-Supervised Difference Detection for Weakly-Supervised Semantic Segmentation","code":"https://github.com/shimoda-uec/ssdd","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":7,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":46,"model":"BoxSup","metrics":{"Mean IoU":"64.6%"},"uses_additional_data":false,"paper_date":"2015-03-05","paper":"/paper/boxsup-exploiting-bounding-boxes-to-supervise","paper_url":"http://arxiv.org/abs/1503.01640v2","paper_title":"BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":47,"model":"PSA w/ EADER DeepLab (Xception-65)","metrics":{"Mean IoU":"63.8%"},"uses_additional_data":false,"paper_date":"2020-11-09","paper":"/paper/find-it-if-you-can-end-to-end-adversarial","paper_url":"https://arxiv.org/abs/2011.04626v1","paper_title":"Find it if You Can: End-to-End Adversarial Erasing for Weakly-Supervised Semantic Segmentation","code":"https://github.com/ErikStammes/EADER","n_code_links":1,"syntology":null},{"rank_in_archive_order":48,"model":"ESPNet","metrics":{"Mean IoU":"63.01%"},"uses_additional_data":false,"paper_date":"2018-03-19","paper":"/paper/espnet-efficient-spatial-pyramid-of-dilated","paper_url":"http://arxiv.org/abs/1803.06815v3","paper_title":"ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":8,"syntology":{"n_ran":4,"n_unverified":6,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":49,"model":"FCN (VGG-16)","metrics":{"Mean IoU":"62.2%"},"uses_additional_data":true,"paper_date":"2014-11-14","paper":"/paper/fully-convolutional-networks-for-semantic-1","paper_url":"http://arxiv.org/abs/1411.4038v2","paper_title":"Fully Convolutional Networks for Semantic Segmentation","code":"https://github.com/pochih/fcn-pytorch","n_code_links":51,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":50,"model":"G2","metrics":{"Mean IoU":"56.7%"},"uses_additional_data":false,"paper_date":"2017-01-28","paper":"/paper/exploiting-saliency-for-object-segmentation","paper_url":"http://arxiv.org/abs/1701.08261v2","paper_title":"Exploiting saliency for object segmentation from image level labels","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":51,"model":"CK","metrics":{"Mean IoU":"51.6%"},"uses_additional_data":false,"paper_date":"2014-07-07","paper":"/paper/simultaneous-detection-and-segmentation","paper_url":"http://arxiv.org/abs/1407.1808v1","paper_title":"Simultaneous Detection and Segmentation","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"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":27,"rows_with_any_sample_ran":20,"distinct_papers_with_graph_line":22,"distinct_papers_with_any_sample_ran":16,"samples_over_distinct_papers":{"n_ran":105,"n_unverified":169,"n_samples":274,"n_pointer_only_licence":93,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":160,"n_unverified":240,"n_samples":400,"n_pointer_only_licence":146,"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"}}}