Papers › Feature-Proxy Transformer for Few-Shot Segmentation
Feature-Proxy Transformer for Few-Shot Segmentation
Jian-Wei Zhang, Yifan Sun, Yi Yang, Wei Chen
Few-shot segmentation (FSS) aims at performing semantic segmentation on novel classes given a few annotated support samples. With a rethink of recent advances, we find that the current FSS framework has deviated far from the supervised segmentation framework: Given the deep features, FSS methods typically use an intricate decoder to perform sophisticated pixel-wise matching, while the supervised segmentation methods use a simple linear classification head. Due to the intricacy of the decoder and its matching pipeline, it is not easy to follow such an FSS framework. This paper revives the straightforward framework of "feature extractor + linear classification head" and proposes a novel Feature-Proxy Transformer (FPTrans) method, in which the "proxy" is the vector representing a semantic class in the linear classification head. FPTrans has two keypoints for learning discriminative features and representative proxies: 1) To better utilize the limited support samples, the feature extractor makes the query interact with the support features from the bottom to top layers using a novel prompting strategy. 2) FPTrans uses multiple local background proxies (instead of a single one) because the background is not homogeneous and may contain some novel foreground regions. These two keypoints are easily integrated into the vision transformer backbone with the prompting mechanism in the transformer. Given the learned features and proxies, FPTrans directly compares their cosine similarity for segmentation. Although the framework is straightforward, we show that FPTrans achieves competitive FSS accuracy on par with state-of-the-art decoder-based methods.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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.
Syntology holds a reference implementation of Feature-Proxy Transformer (FPTrans), generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Feature-Proxy Transformer (FPTrans)') (how to connect); the free check have('2210.06908') needs no token.
For agents, on Syntology's MCP service (how to connect):
get_citation_path(paper_1="2210.06908", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2210.06908")
Code
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
Not run by Syntology. Nothing on this page verifies that the listed code works.
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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.
1 assembly on this paper: 0 harvested, 1 generated.
generated Assembly for Feature-Proxy Transformer (FPTrans) (graph method: Feature-Proxy Transformer (FPTrans)), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).
label matches by construction: the code was generated for this method (not judged by a model)
- compute_fptrans_probability entry · level 3 · ran · our draft was wrong ·
adfc1b281fdc99fec3745caf88ec4690a0e538570616ceaa51ec4e995f97fab8
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="2210.06908") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Few-Shot Semantic Segmentation | COCO-20i (1-shot) | FPTrans (DeiT-B/16) | Mean IoU | 47 | #20 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (1-shot) | FPTrans (ViT-B/16) | Mean IoU | 42 | #52 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | FPTrans (DeiT-B/16) | Mean IoU | 58.9 | #7 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | FPTrans (ViT-B/16) | Mean IoU | 53.8 | #23 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i -> Pascal VOC (1-shot) | FPTrans (DeiT-B/16) | Mean IoU | 69.7 | #4 of 13 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i -> Pascal VOC (1-shot) | FPTrans (ViT-B/16) | Mean IoU | 67.6 | #7 of 13 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i -> Pascal VOC (5-shot) | FPTrans (DeiT-B/16) | Mean IoU | 79.3 | #1 of 12 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i -> Pascal VOC (5-shot) | FPTrans (ViT-B/16) | Mean IoU | 76.9 | #4 of 12 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | FPTrans (DeiT-B/16) | Mean IoU | 68.8 | #16 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | FPTrans (ViT-B/16) | Mean IoU | 64.7 | #55 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | FPTrans (DeiT-B/16) | Mean IoU | 78 | #4 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | FPTrans (ViT-B/16) | Mean IoU | 73.7 | #12 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
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