Papers › Eliminating Feature Ambiguity for Few-Shot Segmentation

Eliminating Feature Ambiguity for Few-Shot Segmentation

13 Jul 2024arXiv:2407.09842archive 2025-07-28

Qianxiong Xu, Guosheng Lin, Chen Change Loy, Cheng Long, Ziyue Li, Rui Zhao

Recent advancements in few-shot segmentation (FSS) have exploited pixel-by-pixel matching between query and support features, typically based on cross attention, which selectively activate query foreground (FG) features that correspond to the same-class support FG features. However, due to the large receptive fields in deep layers of the backbone, the extracted query and support FG features are inevitably mingled with background (BG) features, impeding the FG-FG matching in cross attention. Hence, the query FG features are fused with less support FG features, i.e., the support information is not well utilized. This paper presents a novel plug-in termed ambiguity elimination network (AENet), which can be plugged into any existing cross attention-based FSS methods. The main idea is to mine discriminative query FG regions to rectify the ambiguous FG features, increasing the proportion of FG information, so as to suppress the negative impacts of the doped BG features. In this way, the FG-FG matching is naturally enhanced. We plug AENet into three baselines CyCTR, SCCAN and HDMNet for evaluation, and their scores are improved by large margins, e.g., the 1-shot performance of SCCAN can be improved by 3.0%+ on both PASCAL-5ⁱ and COCO-20ⁱ. The code is available at https://github.com/Sam1224/AENet.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 24 code samples harvested from 1 repository linked to this paper: 21 ran (of which 3 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 11 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 10 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 24 samples from 1 repository, 21 ran (10 with no instrument failure; 11 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 21 samples that ran have no recorded date.

sam1224/aenet officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 24 samples, 21 ran (11 instrument-failed) · 3 unverified 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

24 samples harvested: 21 ran (of which 3 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 11 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
10ran · our draft was wrong
1ran; the contract check could not run
8ran
3unverified

Licence: 24 of the 24 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 sam1224/aenet. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

sam1224/aenet official repository 24 samples, 21 ran (11 instrument-failed) · 3 unverified
DiscAdaptor SCCAN_CyCTR/model/cyc_transformer_plus.py ran · metamorphic tier: deterministic licence not identified · pointer only · d831310b2e245710 · report fixture: returned DiscAdaptor · level recorded 2026-09-22
FFN in 37 papers SCCAN_CyCTR/model/cyc_transformer_plus.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 917577c7e4da6b90 · report fixture: returned FFN · level recorded 2026-09-22
Mlp in 102 papers SCCAN_CyCTR/model/cyc_transformer_plus.py ran · metamorphic tier: deterministic licence not identified · pointer only · 130d72a3eeda8859 · report fixture: returned Mlp · level recorded 2026-09-22
MyCrossAttention SCCAN_CyCTR/model/cyc_transformer_plus.py ran licence not identified · pointer only · 34f245e815c6607b · report fixture: signature q:Tensor/3/float, k:Tensor/3/float, v:Tensor/3/float, supp_valid_mask:Tensor/2/bool, supp_mask:Tensor/2/int, cyc:bool/0/bool · returned Tensor · level recorded 2026-09-24
SinePositionalEncoding SCCAN_CyCTR/model/cyc_transformer_plus.py ran licence not identified · pointer only · 17baacbf828cedd7 · report fixture: signature mask:Tensor/3/bool · returned Tensor · level recorded 2026-09-24
Weighted_GAP in 15 papers
census: 3 implementations from 12 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32 · arg 2: rank 4, kind float, dtype float32
HDMNet/model/HDMNetPlus.py ran · our draft was wrong fingerprinted no licence file found · pointer only · df77cb77dfe58d6d · report fixture: signature supp_feat:Tensor/4/float, mask:Tensor/4/float · returned Tensor · level recorded, date not recorded
conv3x3 in 1,376 papers HDMNet/model/resnet.py ran · our draft was wrong no licence file found · pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
find_bbox HDMNet/util/get_weak_anns.py ran · honoured contract fingerprinted licence not identified · pointer only · 0086d054a8b3d6f3 · report fixture: signature mask:ndarray/2/int · returned ndarray · level recorded 2026-09-24
get_gram_matrix in 9 papers
census: 1 implementation from 5 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
HDMNet/model/HDMNetPlus.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 7feaf1fceef927fe · report fixture: signature fea:Tensor/4/float · returned Tensor · level recorded, date not recorded
get_similarity in 17 papers
census: 3 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 4, kind float, dtype float32 · arg 2: rank 4, kind float, dtype float32 · arg 3: rank 3, kind int, dtype int64
HDMNet/model/HDMNetPlus.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 878c68bef4a644c0 · report fixture: signature q:Tensor/4/float, s:Tensor/4/float, mask:Tensor/3/int · returned Tensor · level recorded, date not recorded
get_vgg16_layer in 7 papers HDMNet/model/PSPNet.py ran · our draft was wrong no licence file found · pointer only · ad7ba6c4e516607e · report fixture: signature model:callable/0/? · returned tuple · level recorded 2026-09-22
is_image_file in 157 papers HDMNet/util/dataset.py ran · violated contract licence not identified · pointer only · 0684a938c70bf564 · report fixture: signature filename:str/0/str · returned bool · level recorded 2026-09-24
load_cfg_from_cfg_file in 24 papers HDMNet/util/config.py ran · our draft was wrong no licence file found · pointer only · 277a13798d6d6981 · report fixture: signature file:str/0/str · returned CfgNode · level recorded 2026-09-25
make_dataset in 144 papers HDMNet/util/dataset.py ran licence not identified · pointer only · 8f6dc933d4638855 · report fixture: signature split:int/0/int, data_root:str/0/str, data_list:str/0/str, sub_list:list/1/int, filter_intersection:bool/0/bool · returned tuple · level recorded 2026-09-24
make_layers in 155 papers HDMNet/model/vgg.py ran · our draft was wrong no licence file found · pointer only · e31250b969b51841 · report fixture: signature cfg:list/1/int, batch_norm:bool/0/bool · returned Sequential · level recorded 2026-09-22
merge_cfg_from_args HDMNet/util/config.py ran licence not identified · pointer only · 32a3d5463ef45125 · report fixture: signature cfg:dict/0/?, args:Namespace/0/? · returned dict · level recorded 2026-09-24
resnet18 in 432 papers HDMNet/model/resnet.py ran · our draft was wrong no licence file found · pointer only · 40a78e38251055c6 · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-24
resnet34 in 148 papers HDMNet/model/resnet.py ran · our draft was wrong no licence file found · pointer only · 4f6dd0ac332dd50d · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-24
transform_anns HDMNet/util/get_weak_anns.py ran licence not identified · pointer only · ac2dc4c99bd03a34 · report fixture: signature mask:ndarray/2/int, ann_type:str/0/str · returned tuple · level recorded 2026-09-24
vgg11 in 50 papers HDMNet/model/vgg.py ran · our draft was wrong no licence file found · pointer only · 2067e75510fbe85e · report fixture: signature pretrained:bool/0/bool · returned VGG · level recorded 2026-09-24
vgg11_bn in 40 papers HDMNet/model/vgg.py ran · our draft was wrong no licence file found · pointer only · bf96fb236a6b1683 · report fixture: signature pretrained:bool/0/bool · returned VGG · level recorded 2026-09-24
CyCTransformerPlus SCCAN_CyCTR/model/cyc_transformer_plus.py unverified licence not identified · pointer only · 8c32eeb614d96727 · report
MSDeformAttn in 13 papers SCCAN_CyCTR/model/cyc_transformer_plus.py unverified licence not identified · pointer only · b29bc600718c53ee · report
merge_cfg_from_list in 24 papers HDMNet/util/config.py unverified licence not identified · pointer only · b925dc5fd8492c34 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for AENet (graph method: AENet). 8 bricks; individually on a fixture: 6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. CyCTransformerPlus entry · level 0 · unverified · 8c32eeb614d96727
  2. DiscAdaptor model · level 1 · ran · d831310b2e245710
  3. FFN helper · level 1 · ran · 917577c7e4da6b90
  4. MSDeformAttn helper · level 0 · unverified · b29bc600718c53ee
  5. MyCrossAttention model · level 1 · ran · 34f245e815c6607b
  6. SinePositionalEncoding helper · level 1 · ran · 17baacbf828cedd7
  7. Mlp helper · level 1 · ran · 130d72a3eeda8859
  8. _is_power_of_2 helper · level 1 · ran · violated contract · 2b45e8897cb1e2ea

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2407.09842") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Few-Shot Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Semantic Segmentation COCO-20i (1-shot) AENet (ResNet-50) FB-IoU 74.4 #8 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) AENet (ResNet-50) Mean IoU 51.3 #8 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) AENet (VGG-16) FB-IoU 71.8 #27 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) AENet (VGG-16) Mean IoU 46.4 #27 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) AENet (ResNet-50) FB-IoU 78.5 #10 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) AENet (ResNet-50) Mean IoU 57.1 #10 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) AENet (VGG-16) FB-IoU 74.3 #26 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) AENet (VGG-16) Mean IoU 52.8 #26 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) AENet (ResNet-50) FB-IoU 81.2 #7 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) AENet (ResNet-50) Mean IoU 70.3 #7 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) AENet (VGG-16) FB-IoU 79.0 #38 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) AENet (VGG-16) Mean IoU 66.6 #38 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) AENet (ResNet-50) FB-IoU 84.5 #9 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) AENet (ResNet-50) Mean IoU 74.2 #9 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) AENet (VGG-16) FB-IoU 81.8 #36 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) AENet (VGG-16) Mean IoU 70.6 #36 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.

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