{"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/context-encoding-for-semantic-segmentation","title":"Context Encoding for Semantic Segmentation","arxiv_id":"1803.08904","date":"2018-03-23","proceeding":"CVPR 2018 6","authors":["Hang Zhang","Kristin Dana","Jianping Shi","Zhongyue Zhang","Xiaogang Wang","Ambrish Tyagi","Amit Agrawal"],"abstract":"Recent work has made significant progress in improving spatial resolution for\npixelwise labeling with Fully Convolutional Network (FCN) framework by\nemploying Dilated/Atrous convolution, utilizing multi-scale features and\nrefining boundaries. In this paper, we explore the impact of global contextual\ninformation in semantic segmentation by introducing the Context Encoding\nModule, which captures the semantic context of scenes and selectively\nhighlights class-dependent featuremaps. The proposed Context Encoding Module\nsignificantly improves semantic segmentation results with only marginal extra\ncomputation cost over FCN. Our approach has achieved new state-of-the-art\nresults 51.7% mIoU on PASCAL-Context, 85.9% mIoU on PASCAL VOC 2012. Our single\nmodel achieves a final score of 0.5567 on ADE20K test set, which surpass the\nwinning entry of COCO-Place Challenge in 2017. In addition, we also explore how\nthe Context Encoding Module can improve the feature representation of\nrelatively shallow networks for the image classification on CIFAR-10 dataset.\nOur 14 layer network has achieved an error rate of 3.45%, which is comparable\nwith state-of-the-art approaches with over 10 times more layers. The source\ncode for the complete system are publicly available.","url_abs":"http://arxiv.org/abs/1803.08904v1","url_pdf":"http://arxiv.org/pdf/1803.08904v1.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":"context-encoding-for-semantic-segmentation","repo_url":"https://github.com/zhanghang1989/PyTorch-Encoding","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"context-encoding-for-semantic-segmentation","repo_url":"https://github.com/CWanli/myencoding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"context-encoding-for-semantic-segmentation","repo_url":"https://github.com/Praveen94/pytorch-encoding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"context-encoding-for-semantic-segmentation","repo_url":"https://github.com/RyanHTR/PyTorch-Encoding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"context-encoding-for-semantic-segmentation","repo_url":"https://github.com/etmwb/cvsegmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"context-encoding-for-semantic-segmentation","repo_url":"https://github.com/kmaninis/pytorch-encoding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"context-encoding-for-semantic-segmentation","repo_url":"https://github.com/xllau/PyTorch-Encoding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"context-encoding-for-semantic-segmentation","repo_url":"https://github.com/zhusiling/EncNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"context-encoding-for-semantic-segmentation","repo_url":"https://github.com/zhusiling/Pytorch-Encoding-boundary","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"context-encoding-for-semantic-segmentation","repo_url":"https://github.com/PaddlePaddle/PaddleSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"context-encoding-for-semantic-segmentation","repo_url":"https://github.com/justld/ENCNet_paddle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"context-encoding-for-semantic-segmentation","repo_url":"https://github.com/open-mmlab/mmsegmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"thermal-image-segmentation","task_name":"Thermal Image Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"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":"fcn","method_name":"FCN"},{"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":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"syncbn","method_name":"SyncBN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"EncNet","rank_in_archive_order":200,"of":235,"metrics":{"Test Score":"55.67","Validation mIoU":"44.65"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k-val","task":"Semantic Segmentation","dataset":"ADE20K val","model":"EncNet (ResNet-101)","rank_in_archive_order":85,"of":95,"metrics":{"mIoU":"44.65"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-pascal-context","task":"Semantic Segmentation","dataset":"PASCAL Context","model":"EncNet (ResNet-101)","rank_in_archive_order":50,"of":66,"metrics":{"mIoU":"51.7"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"EncNet","rank_in_archive_order":7,"of":51,"metrics":{"Mean IoU":"85.9%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"EncNet (ResNet-101)","rank_in_archive_order":21,"of":51,"metrics":{"Mean IoU":"82.9%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.08904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.08904"}},"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/PaddlePaddle/PaddleSeg","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Praveen94/pytorch-encoding","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/CWanli/myencoding","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhanghang1989/PyTorch-Encoding","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/etmwb/cvsegmentation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhusiling/Pytorch-Encoding-boundary","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/justld/ENCNet_paddle","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-mmlab/mmsegmentation","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kmaninis/pytorch-encoding","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/RyanHTR/PyTorch-Encoding","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhusiling/EncNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xllau/PyTorch-Encoding","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":1,"unverified":7},"by_repo_kind":{"listed":{"samples":8,"ran":1,"repositories":2}},"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":7,"samples":[{"code_sha256_prefix":"20eb3e6b0aba73e4","entry":"get_test_config","repo":"justld/ENCNet_paddle","repo_kind":"listed","path":"val.py","file_url":"https://github.com/justld/ENCNet_paddle/blob/HEAD/val.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"20eb3e6b0aba73e4"}},{"code_sha256_prefix":"ccb24f9418500942","entry":"get_city_pairs","repo":"etmwb/cvsegmentation","repo_kind":"listed","path":"cvss/datasets/cityscapes.py","file_url":"https://github.com/etmwb/cvsegmentation/blob/HEAD/cvss/datasets/cityscapes.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"ccb24f9418500942"}},{"code_sha256_prefix":"062e32cfbd653f5e","entry":"get_city_pairs","repo":"etmwb/cvsegmentation","repo_kind":"listed","path":"cvss/datasets/cityscapescoarse.py","file_url":"https://github.com/etmwb/cvsegmentation/blob/HEAD/cvss/datasets/cityscapescoarse.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"062e32cfbd653f5e"}},{"code_sha256_prefix":"d8fa6abe733ae073","entry":"get_deepten","repo":"etmwb/cvsegmentation","repo_kind":"listed","path":"cvss/models/deepten.py","file_url":"https://github.com/etmwb/cvsegmentation/blob/HEAD/cvss/models/deepten.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"d8fa6abe733ae073"}},{"code_sha256_prefix":"a67af4c02a68b8dd","entry":"get_deepten_resnet50_minc","repo":"etmwb/cvsegmentation","repo_kind":"listed","path":"cvss/models/deepten.py","file_url":"https://github.com/etmwb/cvsegmentation/blob/HEAD/cvss/models/deepten.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"a67af4c02a68b8dd"}},{"code_sha256_prefix":"17ed938d47df8418","entry":"get_folder_images","repo":"etmwb/cvsegmentation","repo_kind":"listed","path":"cvss/datasets/folder.py","file_url":"https://github.com/etmwb/cvsegmentation/blob/HEAD/cvss/datasets/folder.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"17ed938d47df8418"}},{"code_sha256_prefix":"61402045af693de1","entry":"short_hash","repo":"etmwb/cvsegmentation","repo_kind":"listed","path":"cvss/models/model_store.py","file_url":"https://github.com/etmwb/cvsegmentation/blob/HEAD/cvss/models/model_store.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"61402045af693de1"}},{"code_sha256_prefix":"f8b881dae14f02c3","entry":"test_batchify_fn","repo":"etmwb/cvsegmentation","repo_kind":"listed","path":"cvss/datasets/base.py","file_url":"https://github.com/etmwb/cvsegmentation/blob/HEAD/cvss/datasets/base.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"f8b881dae14f02c3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}