{"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/rethinking-atrous-convolution-for-semantic","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","arxiv_id":"1706.05587","date":"2017-06-17","proceeding":null,"authors":["Liang-Chieh Chen","George Papandreou","Florian Schroff","Hartwig Adam"],"abstract":"In this work, we revisit atrous convolution, a powerful tool to explicitly\nadjust filter's field-of-view as well as control the resolution of feature\nresponses computed by Deep Convolutional Neural Networks, in the application of\nsemantic image segmentation. To handle the problem of segmenting objects at\nmultiple scales, we design modules which employ atrous convolution in cascade\nor in parallel to capture multi-scale context by adopting multiple atrous\nrates. Furthermore, we propose to augment our previously proposed Atrous\nSpatial Pyramid Pooling module, which probes convolutional features at multiple\nscales, with image-level features encoding global context and further boost\nperformance. We also elaborate on implementation details and share our\nexperience on training our system. The proposed `DeepLabv3' system\nsignificantly improves over our previous DeepLab versions without DenseCRF\npost-processing and attains comparable performance with other state-of-art\nmodels on the PASCAL VOC 2012 semantic image segmentation benchmark.","url_abs":"http://arxiv.org/abs/1706.05587v3","url_pdf":"http://arxiv.org/pdf/1706.05587v3.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":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/2023-MindSpore-1/ms-code-167","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/AutomatedAI/deeplab_inference","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/AutomatedAI/deeplab_segmentation_example","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/BebDong/MXNetSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/DLWK/EANet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/DarkGeekMS/Semantic_Segmentation_Models_Keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/EdwinAlegria/object_semantic_deeplabv3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/HqWei/Semantic-Segmentation-with-Full-Convolutional-Neural-Network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/IRVLab/SUIM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/IRVLab/SUIM-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/JWuzyk/CudaVisionProject","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/JanMarcelKezmann/TensorFlow-Advanced-Segmentation-Models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/JinyongJeong/DeeplabV3_Apolloscape_and_CityScape","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/KPMG-wiseuniv/AI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/NaturalHistoryMuseum/semantic-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/Popcorn-sugar/Deep_v2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/Robinatp/Deeplab_Tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/Syarujianai/deeplab-commented","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/TheTrveAnthony/no-Green","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/VainF/DeepLabV3Plus-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/Vignesh-95/cnn-semantic-segmentation-satellite-images","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/akkaze/cnn-without-any-downsampling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/chenmengyang/rename_later","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/chenxi116/DeepLabv3.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/czarmanu/sentinel_lakeice","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/dajes/DensePose-TorchScript","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/ensta-u2is/deeplabv3plus-muad-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/fregu856/deeplabv3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/giannifranchi/deeplabv3-superpixelmix","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/giovanniguidi/deeplabV3-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/giovanniguidi/deeplabV3_Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/guglielmocamporese/hands-segmentation-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/heidongxianhau/deeplab2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/it6aidl/outdoorsegmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/jbardelli/Petrographic-Image-Segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/kdha0727/cancer-instance-segmentation-from-tissue","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/kekeller/semantic_soy_deeplabv3plus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/leimao/DeepLab-V3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/leimao/DeepLab_v3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/leonardoaraujosantos/seg_atrous","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/lewandofskee/MobileMamba","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/mathildor/DeepLab-v3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/msminhas93/deeplabv3finetuning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/naver-ai/BlendNeRF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/parachutel/deeplabv3plus_on_Mapillary_Vistas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/pranoy-panda/multi_class_segmentation_deeplabv3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/rishizek/tensorflow-deeplab-v3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/samson6460/tf2_Segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/sharifelguindi/DeepLab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/sthalles/deeplab_v3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/stigma0617/VoVNet-DeepLabV3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/tensorflow/models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/tensorflow/models/tree/master/research/deeplab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/udacity/MLND-CN-Capstone-TGSImage","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/xahidbuffon/SUIM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/xahidbuffon/SVAM-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/zhangzjn/emo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/zhangzjn/emov2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/zxleong/GPRNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/2023-MindSpore-1/ms-code-170","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/res2net_deeplabv3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/2023-MindSpore-4/Code1/tree/main/DeepLabv3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/2023-MindSpore-4/Code10/tree/main/DeepLabv3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/2023-MindSpore-4/Code14/tree/main/res2net_deeplabv3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/2024-MindSpore-1/Code4/tree/main/DeepLabv3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/Burf/tfdetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/Media-Smart/vedaseg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/Mind23-2/MindCode-33","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/Mind23-2/MindCode-39","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/MindSpore-paper-code-3/code9/tree/main/DeepLabv3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/MindSpore-paper-code-3/code9/tree/main/ResNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/PaddlePaddle/PaddleSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/bonlime/keras-deeplab-v3-plus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/mindspore-ai/models/tree/master/official/cv/deeplabv3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/pytorch/vision","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"rethinking-atrous-convolution-for-semantic","repo_url":"https://github.com/xiuyu0000/papers_with_examples/tree/main/deeplabv3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"2d-semantic-segmentation","task_name":"2D Semantic Segmentation"},{"task_slug":"dichotomous-image-segmentation","task_name":"Dichotomous Image Segmentation"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"thermal-image-segmentation","task_name":"Thermal Image Segmentation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"aspp","method_name":"ASPP"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"deeplabv3","method_name":"DeepLabv3"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"polynomial-rate-decay","method_name":"Polynomial Rate Decay"},{"method_slug":"randomhorizontalflip","method_name":"Random Horizontal Flip"},{"method_slug":"random-scaling","method_name":"Random Scaling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sgd-with-momentum","method_name":"SGD with Momentum"},{"method_slug":"spatial-pyramid-pooling","method_name":"Spatial Pyramid Pooling"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/2d-semantic-segmentation-on-wildscenes","task":"2D Semantic Segmentation","dataset":"WildScenes","model":"DeepLabv3 (ResNet-50)","rank_in_archive_order":4,"of":5,"metrics":{"mIoU":"43.37","mIoU (Env DA)":"36.12","mIoU (Temporal DA) ":"43.95"},"uses_additional_data":true},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te1","task":"Dichotomous Image Segmentation","dataset":"DIS-TE1","model":"DeeplabV3+","rank_in_archive_order":20,"of":22,"metrics":{"E-measure":"0.772","HCE":"234","MAE":"0.102","S-Measure":"0.694","max F-Measure":"0.601","weighted F-measure":"0.506"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te2","task":"Dichotomous Image Segmentation","dataset":"DIS-TE2","model":"DeeplabV3+","rank_in_archive_order":20,"of":22,"metrics":{"E-measure":"0.813","HCE":"516","MAE":"0.105","S-Measure":"0.729","max F-Measure":"0.681","weighted F-measure":"0.587"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te3","task":"Dichotomous Image Segmentation","dataset":"DIS-TE3","model":"DeeplabV3+","rank_in_archive_order":20,"of":22,"metrics":{"E-measure":"0.833","HCE":"999","MAE":"0.102","S-Measure":"0.749","max F-Measure":"0.717","weighted F-measure":"0.623"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te4","task":"Dichotomous Image Segmentation","dataset":"DIS-TE4","model":"DeeplabV3+","rank_in_archive_order":19,"of":22,"metrics":{"E-measure":"0.820","HCE":"3709","MAE":"0.111","S-Measure":"0.744","max F-Measure":"0.715","weighted F-measure":"0.621"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-vd","task":"Dichotomous Image Segmentation","dataset":"DIS-VD","model":"DeeplabV3+","rank_in_archive_order":23,"of":24,"metrics":{"E-measure":"0.796","HCE":"1520","MAE":"0.114","S-Measure":"0.716","max F-Measure":"0.660","weighted F-measure":"0.568"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"DeepLabv3 (ResNet-101, coarse)","rank_in_archive_order":43,"of":105,"metrics":{"Mean IoU (class)":"81.3%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes-val","task":"Semantic Segmentation","dataset":"Cityscapes val","model":"DeepLabv3 (Dilated-ResNet-101)","rank_in_archive_order":61,"of":99,"metrics":{"mIoU":"78.5%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"DeepLabv3-JFT","rank_in_archive_order":3,"of":51,"metrics":{"Mean IoU":"86.9%"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012-val","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"DeepLabv3-JFT","rank_in_archive_order":6,"of":29,"metrics":{"mIoU":"82.7%"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-selma","task":"Semantic Segmentation","dataset":"SELMA","model":"DeepLabV3","rank_in_archive_order":3,"of":7,"metrics":{"mIoU":"70.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.05587","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.05587"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pytorch/vision","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tensorflow/models","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/giovanniguidi/deeplabV3_Pytorch","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xahidbuffon/SUIM","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/udacity/MLND-CN-Capstone-TGSImage","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleSeg","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-paper-code-3/code9/tree/main/DeepLabv3","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chenmengyang/rename_later","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leimao/DeepLab_v3","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-4/Code1/tree/main/DeepLabv3","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/msminhas93/deeplabv3finetuning","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sharifelguindi/DeepLab","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Popcorn-sugar/Deep_v2","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/guglielmocamporese/hands-segmentation-pytorch","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IRVLab/SUIM-Net","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chenxi116/DeepLabv3.pytorch","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fregu856/deeplabv3","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stigma0617/VoVNet-DeepLabV3","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JinyongJeong/DeeplabV3_Apolloscape_and_CityScape","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DLWK/EANet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/giannifranchi/deeplabv3-superpixelmix","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/parachutel/deeplabv3plus_on_Mapillary_Vistas","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-ai/models/tree/master/official/cv/deeplabv3","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sthalles/deeplab_v3","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pranoy-panda/multi_class_segmentation_deeplabv3","reach":{"status":"unanswered"}}],"summary":{"ran_honours":1,"ran_draft_wrong":1,"ran":1,"unverified":4},"by_repo_kind":{"listed":{"samples":7,"ran":3,"repositories":4}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"4634c9f4f6898b4d","entry":"label_to_color_image","repo":"Robinatp/Deeplab_Tensorflow","repo_kind":"listed","path":"DeepLab_inference_Demo.py","file_url":"https://github.com/Robinatp/Deeplab_Tensorflow/blob/HEAD/DeepLab_inference_Demo.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4634c9f4f6898b4d"}},{"code_sha256_prefix":"1db5c78d80803361","entry":"normalize_fun","repo":"samson6460/tf2_Segmentation","repo_kind":"listed","path":"utils/data_processing.py","file_url":"https://github.com/samson6460/tf2_Segmentation/blob/HEAD/utils/data_processing.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1db5c78d80803361"}},{"code_sha256_prefix":"b5666228355ff947","entry":"read_img","repo":"samson6460/tf2_Segmentation","repo_kind":"listed","path":"utils/data_processing.py","file_url":"https://github.com/samson6460/tf2_Segmentation/blob/HEAD/utils/data_processing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b5666228355ff947"}},{"code_sha256_prefix":"ce942a958c0ae909","entry":"convert_to_separable_conv","repo":"giannifranchi/deeplabv3-superpixelmix","repo_kind":"listed","path":"network/_deeplab.py","file_url":"https://github.com/giannifranchi/deeplabv3-superpixelmix/blob/HEAD/network/_deeplab.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ce942a958c0ae909"}},{"code_sha256_prefix":"e980799df5aec203","entry":"deeplabv3_hrnetv2_32","repo":"VainF/DeepLabV3Plus-Pytorch","repo_kind":"listed","path":"network/modeling.py","file_url":"https://github.com/VainF/DeepLabV3Plus-Pytorch/blob/HEAD/network/modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e980799df5aec203"}},{"code_sha256_prefix":"c85f2e9d72fb69ec","entry":"deeplabv3_hrnetv2_48","repo":"VainF/DeepLabV3Plus-Pytorch","repo_kind":"listed","path":"network/modeling.py","file_url":"https://github.com/VainF/DeepLabV3Plus-Pytorch/blob/HEAD/network/modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c85f2e9d72fb69ec"}},{"code_sha256_prefix":"0264c7923a17f00c","entry":"deeplabv3_resnet50","repo":"VainF/DeepLabV3Plus-Pytorch","repo_kind":"listed","path":"network/modeling.py","file_url":"https://github.com/VainF/DeepLabV3Plus-Pytorch/blob/HEAD/network/modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0264c7923a17f00c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}