{"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/reducing-information-bottleneck-for-weakly","title":"Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation","arxiv_id":"2110.06530","date":"2021-10-13","proceeding":"NeurIPS 2021 12","authors":["Jungbeom Lee","Jooyoung Choi","Jisoo Mok","Sungroh Yoon"],"abstract":"Weakly supervised semantic segmentation produces pixel-level localization from class labels; however, a classifier trained on such labels is likely to focus on a small discriminative region of the target object. We interpret this phenomenon using the information bottleneck principle: the final layer of a deep neural network, activated by the sigmoid or softmax activation functions, causes an information bottleneck, and as a result, only a subset of the task-relevant information is passed on to the output. We first support this argument through a simulated toy experiment and then propose a method to reduce the information bottleneck by removing the last activation function. In addition, we introduce a new pooling method that further encourages the transmission of information from non-discriminative regions to the classification. Our experimental evaluations demonstrate that this simple modification significantly improves the quality of localization maps on both the PASCAL VOC 2012 and MS COCO 2014 datasets, exhibiting a new state-of-the-art performance for weakly supervised semantic segmentation. The code is available at: https://github.com/jbeomlee93/RIB.","url_abs":"https://arxiv.org/abs/2110.06530v1","url_pdf":"https://arxiv.org/pdf/2110.06530v1.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":"reducing-information-bottleneck-for-weakly","repo_url":"https://github.com/jbeomlee93/rib","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"weakly-supervised-semantic-segmentation-1","task_name":"Weakly supervised Semantic Segmentation"},{"task_slug":"weakly-supervised-semantic-segmentation","task_name":"Weakly-Supervised Semantic Segmentation"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-4","task":"Weakly-Supervised Semantic Segmentation","dataset":"COCO 2014 val","model":"RIB (DeepLabV2-ResNet101, No Saliency)","rank_in_archive_order":20,"of":39,"metrics":{"mIoU":"43.8"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-1","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"RIB+Sal (DeepLabV2-ResNet101)","rank_in_archive_order":44,"of":60,"metrics":{"Mean IoU":"70.0"},"uses_additional_data":true},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-1","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"RIB (DeepLabV2-ResNet101)","rank_in_archive_order":52,"of":60,"metrics":{"Mean IoU":"68.6"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"RIB+Sal (DeepLabV2-ResNet101)","rank_in_archive_order":42,"of":73,"metrics":{"Mean IoU":"70.2"},"uses_additional_data":true},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"RIB (DeepLabV2-ResNet101)","rank_in_archive_order":57,"of":73,"metrics":{"Mean IoU":"68.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.06530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06530"}},"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":"deterministic:regex_extraction","url":"https://github.com/jbeomlee93/RIB","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jbeomlee93/rib","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"repositories":1}},"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":"38d2d83395e002b7","entry":"raw_logit_loss_supp_others_norm","repo":"jbeomlee93/rib","repo_kind":"official","path":"obtain_RIB_CAM.py","file_url":"https://github.com/jbeomlee93/rib/blob/HEAD/obtain_RIB_CAM.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"38d2d83395e002b7"}},{"code_sha256_prefix":"306ac4f14a8c7558","entry":"CAM","repo":"jbeomlee93/rib","repo_kind":"official","path":"net/resnet50_cam.py","file_url":"https://github.com/jbeomlee93/rib/blob/HEAD/net/resnet50_cam.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"306ac4f14a8c7558"}},{"code_sha256_prefix":"1d461ea00886dcae","entry":"Net","repo":"jbeomlee93/rib","repo_kind":"official","path":"net/resnet50_cam.py","file_url":"https://github.com/jbeomlee93/rib/blob/HEAD/net/resnet50_cam.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1d461ea00886dcae"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}