Papers › Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning

Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning

13 Jun 2022arXiv:2206.06122archive 2025-07-28

Yanpeng Sun, Qiang Chen, Xiangyu He, Jian Wang, Haocheng Feng, Junyu Han, Errui Ding, Jian Cheng, Zechao Li, Jingdong Wang

Freezing the pre-trained backbone has become a standard paradigm to avoid overfitting in few-shot segmentation. In this paper, we rethink the paradigm and explore a new regime: fine-tuning a small part of parameters in the backbone. We present a solution to overcome the overfitting problem, leading to better model generalization on learning novel classes. Our method decomposes backbone parameters into three successive matrices via the Singular Value Decomposition (SVD), then only fine-tunes the singular values and keeps others frozen. The above design allows the model to adjust feature representations on novel classes while maintaining semantic clues within the pre-trained backbone. We evaluate our Singular Value Fine-tuning (SVF) approach on various few-shot segmentation methods with different backbones. We achieve state-of-the-art results on both Pascal-5ⁱ and COCO-20ⁱ across 1-shot and 5-shot settings. Hopefully, this simple baseline will encourage researchers to rethink the role of backbone fine-tuning in few-shot settings. The source code and models will be available at https://github.com/syp2ysy/SVF.

PaperPDFConference PDFCodeCode Syntology ran

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 4 code samples harvested from 2 repositories linked to this paper: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community: 3 samples from 1 repository, 1 ran (0 with no instrument failure; 1 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.

No date is recorded for any of the 2 samples that ran: their levels were written before Syntology's graph kept the date.

syp2ysy/SVF officialmentioned in papermentioned on GitHubpaddleSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 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

4 samples harvested: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. 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.

1ran · honoured contract
1ran · our draft was wrong
2unverified

Licence: 0 of the 4 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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”. “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.

syp2ysy/SVF official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
round_to_nearest svf.py ran · honoured contract fingerprinted MIT (permissive) · abd97f26f98fa5b0 · report fixture: signature n:int/0/int, ratio:float/0/float, base_number:int/0/int, allow_rank_eq1:bool/0/bool · returned int · level recorded, date not recorded
zechao-li/SVF-pytorch community 3 samples, 1 ran (1 instrument-failed) · 2 unverified
d_nsvd svf.py ran · our draft was wrong fingerprinted MIT (permissive) · 46c465264fc07006 · report fixture: signature matrix:Tensor/2/float, rank:int/0/int · returned tuple · level recorded, date not recorded
replace_fullrank_with_lowrank svf.py unverified MIT (permissive) · e839efa71c7b59e3 · report
round_to_nearest svf.py unverified MIT (permissive) · 72b4beced0f39b70 · report

Tasks

Few-Shot Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Semantic Segmentation COCO-20i (1-shot) BAM (SVF, ResNet-50) Mean IoU 48.47 #15 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) PFENet (SVF, ResNet-50) Mean IoU 48.02 #17 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) BAM (SVF, VGG-16) Mean IoU 43.76 #39 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) PFENet (SVF, VGG-16) Mean IoU 42.24 #51 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) PFENet (SVF, ResNet-50) Mean IoU 54.38 #20 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) BAM (SVF, ResNet-50) Mean IoU 53.87 #22 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) PFENet (SVF, VGG-16) Mean IoU 49.49 #42 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) BAM (SVF, VGG-16) Mean IoU 49.07 #45 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) BAM (SVF, ResNet-50) FB-IoU 80.13 #15 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) BAM (SVF, ResNet-50) Mean IoU 68.95 #15 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) PFENet (SVF, ResNet-50) FB-IoU 79.07 #20 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) PFENet (SVF, ResNet-50) Mean IoU 68.15 #20 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) BAM (SVF, VGG-16) Mean IoU 64.87 #52 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) PFENet (SVF, VGG-16) Mean IoU 64.33 #58 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) BAM (SVF, ResNet-50) FB-IoU 83.17 #18 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) BAM (SVF, ResNet-50) Mean IoU 72.28 #18 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) PFENet (SVF, ResNet-50) FB-IoU 82.77 #21 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) PFENet (SVF, ResNet-50) Mean IoU 71.82 #21 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) PFENet (SVF, VGG-16) Mean IoU 69.8 #44 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) BAM (SVF, VGG-16) Mean IoU 69.11 #52 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