Papers › HM: Hybrid Masking for Few-Shot Segmentation

HM: Hybrid Masking for Few-Shot Segmentation

24 Mar 2022arXiv:2203.12826archive 2025-07-28

Seonghyeon Moon, Samuel S. Sohn, Honglu Zhou, Sejong Yoon, Vladimir Pavlovic, Muhammad Haris Khan, Mubbasir Kapadia

We study few-shot semantic segmentation that aims to segment a target object from a query image when provided with a few annotated support images of the target class. Several recent methods resort to a feature masking (FM) technique to discard irrelevant feature activations which eventually facilitates the reliable prediction of segmentation mask. A fundamental limitation of FM is the inability to preserve the fine-grained spatial details that affect the accuracy of segmentation mask, especially for small target objects. In this paper, we develop a simple, effective, and efficient approach to enhance feature masking (FM). We dub the enhanced FM as hybrid masking (HM). Specifically, we compensate for the loss of fine-grained spatial details in FM technique by investigating and leveraging a complementary basic input masking method. Experiments have been conducted on three publicly available benchmarks with strong few-shot segmentation (FSS) baselines. We empirically show improved performance against the current state-of-the-art methods by visible margins across different benchmarks. Our code and trained models are available at: https://github.com/moonsh/HM-Hybrid-Masking

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 1 code sample harvested from 1 repository linked to this paper: 0 ran · 1 unverified.

By repository: official repository: 1 sample from 1 repository, 0 ran (0 with no instrument failure; 0 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.

moonsh/hm-hybrid-masking officialmentioned in papermentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 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

1 sample harvested: 0 ran · 1 unverified. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1unverified

Licence: 1 of the 1 sample 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 moonsh/hm-hybrid-masking. “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 “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.

moonsh/hm-hybrid-masking official repository 1 sample, 0 ran · 1 unverified
HypercorrSqueezeNetwork hsnet.py unverified no licence file found · pointer only · 3af45cd405738bcc · 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 Hybrid Masking (HM) (graph method: Hybrid Masking (HM)). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

  1. HypercorrSqueezeNetwork entry · level 0 · unverified · 3af45cd405738bcc

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="2203.12826") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Few-Shot Semantic SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Semantic Segmentation COCO-20i (1-shot) HSNet (HM, ResNet-101) FB-IoU 71.5 #24 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) HSNet (HM, ResNet-101) Mean IoU 46.5 #24 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) ASNet (HM, ResNet-101) FB-IoU 71.1 #30 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) ASNet (HM, ResNet-101) Mean IoU 45.9 #30 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) ASNet (HM, ResNet-50) FB-IoU 70.4 #36 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) ASNet (HM, ResNet-50) Mean IoU 44.7 #36 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) HSNet (HM, ResNet-50) FB-IoU 70.8 #37 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) HSNet (HM, ResNet-50) Mean IoU 44.3 #37 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) VAT (HM, ResNet-50) FB-IoU 70 #44 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) VAT (HM, ResNet-50) Mean IoU 43.2 #44 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) ASNet (HM, ResNet-101) FB-IoU 73.3 #35 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) ASNet (HM, ResNet-101) Mean IoU 50.6 #35 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) HSNet (HM, ResNet-101) FB-IoU 72.9 #36 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) HSNet (HM, ResNet-101) Mean IoU 50.6 #36 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) HSNet (HM, ResNet-50) FB-IoU 72.2 #43 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) HSNet (HM, ResNet-50) Mean IoU 49.4 #43 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) ASNet (HM, ResNet-50) FB-IoU 72.2 #46 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) ASNet (HM, ResNet-50) Mean IoU 48.4 #46 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) VAT (HM, ResNet-50) FB-IoU 71.8 #47 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) VAT (HM, ResNet-50) Mean IoU 48.3 #47 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i -> Pascal VOC (1-shot) HSNet (HM, ResNet-101) Mean IoU 66.5 #8 of 13 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i -> Pascal VOC (1-shot) HSNet (HM, ResNet-50) Mean IoU 65.2 #9 of 13 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i -> Pascal VOC (1-shot) VAT (HM, ResNet-50) Mean IoU 65.1 #10 of 13 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i -> Pascal VOC (5-shot) HSNet (HM, ResNet-101) Mean IoU 70.9 #7 of 12 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i -> Pascal VOC (5-shot) HSNet (HM, ResNet-50) Mean IoU 69.7 #8 of 12 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i -> Pascal VOC (5-shot) VAT (HM, ResNet-50) Mean IoU 69.7 #9 of 12 Archive leaderboard report
Few-Shot Semantic Segmentation FSS-1000 (1-shot) VAT (HM, ResNet-101) Mean IoU 90.2 #5 of 24 Archive leaderboard report
Few-Shot Semantic Segmentation FSS-1000 (1-shot) VAT (HM, ResNet-50) Mean IoU 89.4 #9 of 24 Archive leaderboard report
Few-Shot Semantic Segmentation FSS-1000 (1-shot) HSNet (HM, ResNet-101) Mean IoU 87.8 #14 of 24 Archive leaderboard report
Few-Shot Semantic Segmentation FSS-1000 (1-shot) HSNet (HM, ResNet-50) Mean IoU 87.1 #16 of 24 Archive leaderboard report
Few-Shot Semantic Segmentation FSS-1000 (5-shot) VAT (HM, ResNet-101) Mean IoU 90.5 #6 of 22 Archive leaderboard report
Few-Shot Semantic Segmentation FSS-1000 (5-shot) VAT (HM, ResNet-50) Mean IoU 89.9 #8 of 22 Archive leaderboard report
Few-Shot Semantic Segmentation FSS-1000 (5-shot) HSNet (HM, ResNet-101) Mean IoU 88.5 #14 of 22 Archive leaderboard report
Few-Shot Semantic Segmentation FSS-1000 (5-shot) HSNet (HM, ResNet-50) Mean IoU 88 #16 of 22 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) VAT (HM, ResNet-101) FB-IoU 79.4 #23 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) VAT (HM, ResNet-101) Mean IoU 67.8 #23 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) HSNet (HM, ResNet-101) FB-IoU 77.8 #36 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) HSNet (HM, ResNet-101) Mean IoU 66.7 #36 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) VAT (HM, ResNet-50) FB-IoU 77.1 #43 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) VAT (HM, ResNet-50) Mean IoU 65.8 #43 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) HSNet (HM, ResNet-50) FB-IoU 76.5 #51 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) HSNet (HM, ResNet-50) Mean IoU 65 #51 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) VAT (HM, ResNet-101) FB-IoU 81.5 #32 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) VAT (HM, ResNet-101) Mean IoU 70.9 #32 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) HSNet (HM, ResNet-101) FB-IoU 79.7 #47 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) HSNet (HM, ResNet-101) Mean IoU 69.3 #47 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) VAT (HM, ResNet-50) FB-IoU 78.5 #59 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) VAT (HM, ResNet-50) Mean IoU 68.2 #59 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) HSNet (HM, ResNet-50) FB-IoU 77.7 #63 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) HSNet (HM, ResNet-50) Mean IoU 67.1 #63 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