Papers › Weakly-Supervised Semantic Segmentation via Sub-category Exploration

Weakly-Supervised Semantic Segmentation via Sub-category Exploration

3 Aug 2020CVPR 2020 6arXiv:2008.01183archive 2025-07-28

Yu-Ting Chang, Qiaosong Wang, Wei-Chih Hung, Robinson Piramuthu, Yi-Hsuan Tsai, Ming-Hsuan Yang

Existing weakly-supervised semantic segmentation methods using image-level annotations typically rely on initial responses to locate object regions. However, such response maps generated by the classification network usually focus on discriminative object parts, due to the fact that the network does not need the entire object for optimizing the objective function. To enforce the network to pay attention to other parts of an object, we propose a simple yet effective approach that introduces a self-supervised task by exploiting the sub-category information. Specifically, we perform clustering on image features to generate pseudo sub-categories labels within each annotated parent class, and construct a sub-category objective to assign the network to a more challenging task. By iteratively clustering image features, the training process does not limit itself to the most discriminative object parts, hence improving the quality of the response maps. We conduct extensive analysis to validate the proposed method and show that our approach performs favorably against the state-of-the-art approaches.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2008.01183")

Code

Syntology Ran 1 of 16 code samples harvested from 1 repository linked to this paper; 15 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: official repository: 16 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Juliachang/SC-CAM officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested; 1 ran; 0 honoured the contract we drafted; 15 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
15unverified

Licence: 0 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from Juliachang/SC-CAM. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

scores Juliachang/SC-CAM/tool/iouutils.py official repository ran · our draft was wrong MIT (permissive) · 4d8fbe9ff0f1714e · report
calculate_class_avg_iou Juliachang/SC-CAM/tool/infer_utils.py official repository unverified MIT (permissive) · 0f3b88f76a1f1b69 · report
cam_npy_to_label_map Juliachang/SC-CAM/tool/camutils.py official repository unverified MIT (permissive) · b991660d9b0a2e9e · report
cls200_sum Juliachang/SC-CAM/train_cls.py official repository unverified MIT (permissive) · ac9ccf112fb4d9db · report
compute_acc Juliachang/SC-CAM/train_cls.py official repository unverified MIT (permissive) · e7b5ceebedb5efe7 · report
convert_mxnet_to_torch Juliachang/SC-CAM/network/resnet38d.py official repository unverified MIT (permissive) · 95dfca01d7656b7c · report
create_class_key_in_dict Juliachang/SC-CAM/create_pseudo_label.py official repository unverified MIT (permissive) · 207543a1e7a80fd3 · report
crop_with_box Juliachang/SC-CAM/tool/imutils.py official repository unverified MIT (permissive) · 1da77dcda491ece7 · report
dict2npy Juliachang/SC-CAM/tool/camutils.py official repository unverified MIT (permissive) · aede9964dd51e4c8 · report
draw_heatmap Juliachang/SC-CAM/tool/camutils.py official repository unverified MIT (permissive) · 361a0bf7cb1e701e · report
draw_heatmap Juliachang/SC-CAM/tool/infer_utils.py official repository unverified MIT (permissive) · b16041930709dec1 · report
generate_merged_label Juliachang/SC-CAM/create_pseudo_label.py official repository unverified MIT (permissive) · 08008d2ed2836147 · report
get_img_path Juliachang/SC-CAM/train_cls.py official repository unverified MIT (permissive) · 0a5d5355f060c563 · report
get_random_crop_box Juliachang/SC-CAM/tool/imutils.py official repository unverified MIT (permissive) · 14cb2e4c07b535f6 · report
make_subclass_label Juliachang/SC-CAM/create_pseudo_label.py official repository unverified MIT (permissive) · 6e46befc4a038fa2 · report
random_crop Juliachang/SC-CAM/tool/imutils.py official repository unverified MIT (permissive) · fab5abda02bc5312 · report

Tasks

ClusteringObjectSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Weakly-Supervised Semantic Segmentation PASCAL VOC 2012 val SC-CAM-ResNet-101 Mean IoU 66.1 #68 of 73 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections