Papers › Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation

Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation

21 Apr 2022arXiv:2204.09903archive 2025-07-28

Chunbo Lang, Binfei Tu, Gong Cheng, Junwei Han

Few-shot segmentation, which aims to segment unseen-class objects given only a handful of densely labeled samples, has received widespread attention from the community. Existing approaches typically follow the prototype learning paradigm to perform meta-inference, which fails to fully exploit the underlying information from support image-mask pairs, resulting in various segmentation failures, e.g., incomplete objects, ambiguous boundaries, and distractor activation. To this end, we propose a simple yet versatile framework in the spirit of divide-and-conquer. Specifically, a novel self-reasoning scheme is first implemented on the annotated support image, and then the coarse segmentation mask is divided into multiple regions with different properties. Leveraging effective masked average pooling operations, a series of support-induced proxies are thus derived, each playing a specific role in conquering the above challenges. Moreover, we devise a unique parallel decoder structure that integrates proxies with similar attributes to boost the discrimination power. Our proposed approach, named divide-and-conquer proxies (DCP), allows for the development of appropriate and reliable information as a guide at the "episode" level, not just about the object cues themselves. Extensive experiments on PASCAL-5i and COCO-20i demonstrate the superiority of DCP over conventional prototype-based approaches (up to 5~10% on average), which also establishes a new state-of-the-art. Code is available at github.com/chunbolang/DCP.

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="2204.09903")

Code

Syntology Ran 12 of 13 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 8 ran · our draft was wrong; 4 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 11 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

chunbolang/DCP officialmentioned in papermentioned on GitHubpytorch 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

13 samples harvested; 12 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

8ran · our draft was wrong
4ran
1unverified

Licence: 1 of the 13 samples is 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 chunbolang/DCP. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

ASPP chunbolang/DCP/model/DCP.py official repository ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · deb925d25beba09d · report
Bottleneck chunbolang/DCP/model/DCP.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 9b6cbc9dee558bd7 · report
ResNet chunbolang/DCP/model/DCP.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 2da49133aa591f02 · report
VGG chunbolang/DCP/model/DCP.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 7aefeb45456c2c53 · report
get_vgg16_layer chunbolang/DCP/model/DCP.py official repository ran · our draft was wrong MIT (permissive) · ad7ba6c4e516607e · report
make_layers chunbolang/DCP/model/DCP.py official repository ran · our draft was wrong MIT (permissive) · 3817cebff2add9fb · report
resnet101 chunbolang/DCP/model/DCP.py official repository ran · our draft was wrong MIT (permissive) · ae93e3b60685c29d · report
resnet152 chunbolang/DCP/model/DCP.py official repository ran · our draft was wrong MIT (permissive) · bacf5d53a01d1e64 · report
resnet50 chunbolang/DCP/model/DCP.py official repository ran · our draft was wrong MIT (permissive) · a5b336b54939f4de · report
vgg16 chunbolang/DCP/model/DCP.py official repository ran · our draft was wrong MIT (permissive) · 0902796de5cc0ba5 · report
vgg16_bn chunbolang/DCP/model/DCP.py official repository ran · our draft was wrong MIT (permissive) · 7495062bfa6820b8 · report
OneModel chunbolang/DCP/model/DCP.py official repository unverified MIT (permissive) · c7581a28a77f6859 · report
Weighted_GAP identical code first harvested elsewhere ran · our draft was wrong fingerprinted licence of this copy not recorded · df77cb77dfe58d6d · report

Tasks

DecoderFew-Shot Semantic SegmentationMeta-LearningSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Semantic Segmentation COCO-20i (1-shot) DCP (ResNet-50) Mean IoU 41.39 #57 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) DCP (ResNet-50) Mean IoU 46.48 #59 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) DCP (ResNet-50) Mean IoU 62.80 #72 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) DCP (ResNet-50) Mean IoU 67.80 #61 of 96 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

Average Pooling

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