Papers › Complementary Patch for Weakly Supervised Semantic Segmentation

Complementary Patch for Weakly Supervised Semantic Segmentation

9 Aug 2021ICCV 2021 10arXiv:2108.03852archive 2025-07-28

Fei Zhang, Chaochen Gu, Chenyue Zhang, Yuchao Dai

Weakly Supervised Semantic Segmentation (WSSS) based on image-level labels has been greatly advanced by exploiting the outputs of Class Activation Map (CAM) to generate the pseudo labels for semantic segmentation. However, CAM merely discovers seeds from a small number of regions, which may be insufficient to serve as pseudo masks for semantic segmentation. In this paper, we formulate the expansion of object regions in CAM as an increase in information. From the perspective of information theory, we propose a novel Complementary Patch (CP) Representation and prove that the information of the sum of the CAMs by a pair of input images with complementary hidden (patched) parts, namely CP Pair, is greater than or equal to the information of the baseline CAM. Therefore, a CAM with more information related to object seeds can be obtained by narrowing down the gap between the sum of CAMs generated by the CP Pair and the original CAM. We propose a CP Network (CPN) implemented by a triplet network and three regularization functions. To further improve the quality of the CAMs, we propose a Pixel-Region Correlation Module (PRCM) to augment the contextual information by using object-region relations between the feature maps and the CAMs. Experimental results on the PASCAL VOC 2012 datasets show that our proposed method achieves a new state-of-the-art in WSSS, validating the effectiveness of our CP Representation and CPN.

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="2108.03852")

Code

Syntology Ran 3 of 15 code samples harvested from 1 repository linked to this paper; 12 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 15 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Ferenas/CPN officialmentioned 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

15 samples harvested; 3 ran; 0 honoured the contract we drafted; 12 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.

2ran · our draft was wrong
1ran · fixture could not drive it
12unverified

Licence: 0 of the 15 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 Ferenas/CPN. “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.

adaptive_min_pooling_loss Ferenas/CPN/train_cpn.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 4c323e44c38f5fb2 · report
do_python_eval Ferenas/CPN/evaluation_cam.py official repository ran · our draft was wrong MIT (permissive) · 4de99c8ad78aceee · report
gap2d Ferenas/CPN/misc/torchutils.py official repository ran · our draft was wrong MIT (permissive) · b2dee97c33d89372 · report
affinity_sparse2dense Ferenas/CPN/misc/indexing.py official repository unverified MIT (permissive) · 40bf8abef0c6e4b2 · report
convert_mxnet_to_torch Ferenas/CPN/network/resnet38d.py official repository unverified MIT (permissive) · 95dfca01d7656b7c · report
edge_to_affinity Ferenas/CPN/misc/indexing.py official repository unverified MIT (permissive) · d3b122efb6e32fed · report
hide_patch Ferenas/CPN/tool/imutils.py official repository unverified MIT (permissive) · 50fe7cd84374ba59 · report
hide_patch_ss Ferenas/CPN/tool/imutils.py official repository unverified MIT (permissive) · 4d5584b87aef6565 · report
max_onehot Ferenas/CPN/tool/imutils.py official repository unverified MIT (permissive) · 94c2437fbb7c88f7 · report
pil_rescale Ferenas/CPN/misc/imutils.py official repository unverified MIT (permissive) · 03816bd33ff47d91 · report
pil_resize Ferenas/CPN/misc/imutils.py official repository unverified MIT (permissive) · 4e4bdca77f683cf7 · report
random_resize_long Ferenas/CPN/misc/imutils.py official repository unverified MIT (permissive) · 802a057433809fc1 · report
split_dataset Ferenas/CPN/misc/torchutils.py official repository unverified MIT (permissive) · 8129bde610e5350b · report
to_one_hot Ferenas/CPN/misc/pyutils.py official repository unverified MIT (permissive) · fa36a8f1f0a5a428 · report
to_transition_matrix Ferenas/CPN/misc/indexing.py official repository unverified MIT (permissive) · 2d78188bd6f7f6dc · report

Tasks

SegmentationSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Weakly-Supervised Semantic Segmentation PASCAL VOC 2012 test CPN Mean IoU 68.5 #54 of 60 Archive leaderboard report
Weakly-Supervised Semantic Segmentation PASCAL VOC 2012 val CPN Mean IoU 67.8 #61 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.

Methods

CAMCPNConvolution

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