Papers › DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions...

DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation

30 Mar 2024arXiv:2404.00380archive 2025-07-28

Sanghyun Jo, Fei Pan, In-Jae Yu, KyungSu Kim

Weakly-supervised semantic segmentation (WSS) ensures high-quality segmentation with limited data and excels when employed as input seed masks for large-scale vision models such as Segment Anything. However, WSS faces challenges related to minor classes since those are overlooked in images with adjacent multiple classes, a limitation originating from the overfitting of traditional expansion methods like Random Walk. We first address this by employing unsupervised and weakly-supervised feature maps instead of conventional methodologies, allowing for hierarchical mask enhancement. This method distinctly categorizes higher-level classes and subsequently separates their associated lower-level classes, ensuring all classes are correctly restored in the mask without losing minor ones. Our approach, validated through extensive experimentation, significantly improves WSS across five benchmarks (VOC: 79.8\%, COCO: 53.9\%, Context: 49.0\%, ADE: 32.9\%, Stuff: 37.4\%), reducing the gap with fully supervised methods by over 84\% on the VOC validation set. Code is available at https://github.com/shjo-april/DHR.

PaperPDFCodeCode 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="2404.00380")

Code

Syntology Ran 9 of 9 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 7 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

shjo-april/DHR officialmentioned in papermentioned on GitHub 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

9 samples harvested; 9 ran; 0 honoured the contract we drafted; 0 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
7ran

Licence: 9 of the 9 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 shjo-april/DHR. “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.

conv1x1 shjo-april/DHR/core/backbones/resnet/model.py official repository ran · our draft was wrong no licence file found · pointer only · 2a80220dabcb742a · report
conv3x3 shjo-april/DHR/core/backbones/resnet/model.py official repository ran · our draft was wrong no licence file found · pointer only · 600ff2c45e0de056 · report
cos_distance_matrix shjo-april/DHR/core/uss/layers.py official repository ran fingerprinted no licence file found · pointer only · 72159f7fc0730f16 · report
get_feature_size shjo-april/DHR/core/uss/utils.py official repository ran fingerprinted no licence file found · pointer only · 4e6823add3e04864 · report
get_onehot shjo-april/DHR/core/datasets.py official repository ran no licence file found · pointer only · 24bae61a0df31758 · report
interpolate_pe shjo-april/DHR/core/uss/utils.py official repository ran fingerprinted no licence file found · pointer only · 72e36a6d1b344ccd · report
resize shjo-april/DHR/core/uss/utils.py official repository ran no licence file found · pointer only · 72c53856189c88e9 · report
transform shjo-april/DHR/core/uss/layers.py official repository ran no licence file found · pointer only · 0c168de9d101c228 · report
untransform shjo-april/DHR/core/uss/layers.py official repository ran fingerprinted no licence file found · pointer only · f800eaf8e169b9ab · report

Tasks

SegmentationSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Weakly-Supervised Semantic Segmentation ADE20K val DHR (Swin-L, Mask2Former) mIoU 32.9 #1 of 1 Archive leaderboard report
Weakly-Supervised Semantic Segmentation COCO 2014 val DHR (Swin-L, Mask2Former) mIoU 56.8 #1 of 39 Archive leaderboard report
Weakly-Supervised Semantic Segmentation COCO-Stuff val DHR (Swin-L, Mask2Former) mIoU 37.4 #1 of 1 Archive leaderboard report
Weakly-Supervised Semantic Segmentation PASCAL Context val DHR (Swin-L, Mask2Former) mIoU 53.6 #1 of 1 Archive leaderboard report
Weakly-Supervised Semantic Segmentation PASCAL VOC 2012 test DHR (Swin-L, Mask2Former) Mean IoU 82.3 #2 of 60 Archive leaderboard report
Weakly-Supervised Semantic Segmentation PASCAL VOC 2012 val DHR (Swin-L, Mask2Former) Mean IoU 82.3 #3 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