Papers › Learning What Not to Segment: A New Perspective on Few-Shot Segmentation

Learning What Not to Segment: A New Perspective on Few-Shot Segmentation

15 Mar 2022CVPR 2022 1arXiv:2203.07615archive 2025-07-28

Chunbo Lang, Gong Cheng, Binfei Tu, Junwei Han

Recently few-shot segmentation (FSS) has been extensively developed. Most previous works strive to achieve generalization through the meta-learning framework derived from classification tasks; however, the trained models are biased towards the seen classes instead of being ideally class-agnostic, thus hindering the recognition of new concepts. This paper proposes a fresh and straightforward insight to alleviate the problem. Specifically, we apply an additional branch (base learner) to the conventional FSS model (meta learner) to explicitly identify the targets of base classes, i.e., the regions that do not need to be segmented. Then, the coarse results output by these two learners in parallel are adaptively integrated to yield precise segmentation prediction. Considering the sensitivity of meta learner, we further introduce an adjustment factor to estimate the scene differences between the input image pairs for facilitating the model ensemble forecasting. The substantial performance gains on PASCAL-5i and COCO-20i verify the effectiveness, and surprisingly, our versatile scheme sets a new state-of-the-art even with two plain learners. Moreover, in light of the unique nature of the proposed approach, we also extend it to a more realistic but challenging setting, i.e., generalized FSS, where the pixels of both base and novel classes are required to be determined. The source code is available at github.com/chunbolang/BAM.

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="2203.07615")

Code

Syntology Ran 14 of 17 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 4 ran · our draft was wrong; 1 ran · fixture could not drive it; 9 ran with no contract checked.

By repository: official repository: 17 samples from 1 repository, 14 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

chunbolang/BAM 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

17 samples harvested; 14 ran; 0 honoured the contract we drafted; 3 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.

4ran · our draft was wrong
1ran · fixture could not drive it
9ran
3unverified

Licence: 0 of the 17 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 chunbolang/BAM. “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.

Weighted_GAP chunbolang/BAM/model/BAM.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · df77cb77dfe58d6d · report
conv3x3 chunbolang/BAM/model/resnet.py official repository ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
find_bbox chunbolang/BAM/util/get_weak_anns.py official repository ran fingerprinted MIT (permissive) · 0086d054a8b3d6f3 · report
get_gram_matrix chunbolang/BAM/model/BAM.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 7feaf1fceef927fe · report
get_vgg16_layer chunbolang/BAM/model/PSPNet.py official repository ran · our draft was wrong MIT (permissive) · ad7ba6c4e516607e · report
is_image_file chunbolang/BAM/util/dataset.py official repository ran MIT (permissive) · 0684a938c70bf564 · report
make_dataset chunbolang/BAM/util/dataset.py official repository ran MIT (permissive) · 8f6dc933d4638855 · report
make_layers chunbolang/BAM/model/vgg.py official repository ran · our draft was wrong MIT (permissive) · e31250b969b51841 · report
merge_cfg_from_args chunbolang/BAM/util/config.py official repository ran MIT (permissive) · 32a3d5463ef45125 · report
resnet18 chunbolang/BAM/model/resnet.py official repository ran MIT (permissive) · 40a78e38251055c6 · report
resnet34 chunbolang/BAM/model/resnet.py official repository ran MIT (permissive) · 4f6dd0ac332dd50d · report
transform_anns chunbolang/BAM/util/get_weak_anns.py official repository ran MIT (permissive) · ac2dc4c99bd03a34 · report
vgg11 chunbolang/BAM/model/vgg.py official repository ran MIT (permissive) · 2067e75510fbe85e · report
vgg11_bn chunbolang/BAM/model/vgg.py official repository ran MIT (permissive) · bf96fb236a6b1683 · report
load_cfg_from_cfg_file chunbolang/BAM/util/config.py official repository unverified MIT (permissive) · 277a13798d6d6981 · report
make_GFSS_dataset chunbolang/BAM/util/dataset.py official repository unverified MIT (permissive) · 6bf9093839138e39 · report
merge_cfg_from_list chunbolang/BAM/util/config.py official repository unverified MIT (permissive) · b925dc5fd8492c34 · report

Tasks

Few-Shot Semantic SegmentationMeta-LearningSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Semantic Segmentation COCO-20i (1-shot) BAM (ResNet-50) Mean IoU 46.23 #29 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) BAM (ResNet-50) learnable parameters (million) 26.7 #29 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) BAM (ResNet-50) Mean IoU 51.16 #31 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) BAM (ResNet-50) learnable parameters (million) 26.7 #31 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) BAM (ResNet-50) Mean IoU 67.81 #22 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) BAM (ResNet-50) Mean IoU 70.91 #31 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

Auxiliary ClassifierAverage PoolingBASEBatch NormalizationConvolutionDilated ConvolutionPSPNetPyramid Pooling ModuleReLU

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