Papers › Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation

Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation

30 Jul 2022arXiv:2208.00306archive 2025-07-28

Zhitong Xiong, Haopeng Li, Xiao Xiang Zhu

Training semantic segmentation models with few annotated samples has great potential in various real-world applications. For the few-shot segmentation task, the main challenge is how to accurately measure the semantic correspondence between the support and query samples with limited training data. To address this problem, we propose to aggregate the learnable covariance matrices with a deformable 4D Transformer to effectively predict the segmentation map. Specifically, in this work, we first devise a novel hard example mining mechanism to learn covariance kernels for the Gaussian process. The learned covariance kernel functions have great advantages over existing cosine similarity-based methods in correspondence measurement. Based on the learned covariance kernels, an efficient doubly deformable 4D Transformer module is designed to adaptively aggregate feature similarity maps into segmentation results. By combining these two designs, the proposed method can not only set new state-of-the-art performance on public benchmarks, but also converge extremely faster than existing methods. Experiments on three public datasets have demonstrated the effectiveness of our method.

PaperPDFCodeCode 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="2208.00306")

Code

Syntology Ran 2 of 2 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 2 ran with no contract checked.

By repository: official repository: 2 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

shadowxzt/dacm-few-shot.pytorch officialmentioned in paperpytorch 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

2 samples harvested; 2 ran; 0 honoured the contract we drafted; 0 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.

2ran

Licence: 2 of the 2 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 shadowxzt/dacm-few-shot.pytorch. “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.

DAttentionModule shadowxzt/dacm-few-shot.pytorch/model/base/multimodal_df.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · adcd53d99f2ea63d · report
LayerNormProxy shadowxzt/dacm-few-shot.pytorch/model/base/multimodal_df.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · 97a403009efc85d8 · report

Tasks

Few-Shot Semantic SegmentationSegmentationSemantic SegmentationSemantic correspondence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Semantic Segmentation COCO-20i (1-shot) DACM (VAT, ResNet-50) FB-IoU 69.4 #46 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) DACM (VAT, ResNet-50) Mean IoU 43 #46 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) DACM (ResNet-50) FB-IoU 68.9 #61 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) DACM (ResNet-50) Mean IoU 40.6 #61 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) DACM (VAT, ResNet-50) FB-IoU 72.9 #44 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) DACM (VAT, ResNet-50) Mean IoU 49.2 #44 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) DACM (ResNet-50) FB-IoU 71.6 #49 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) DACM (ResNet-50) Mean IoU 48.1 #49 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation FSS-1000 (1-shot) DACM (ResNet-101) Mean IoU 90.8 #1 of 24 Archive leaderboard report
Few-Shot Semantic Segmentation FSS-1000 (1-shot) DACM (ResNet-50) Mean IoU 90.7 #2 of 24 Archive leaderboard report
Few-Shot Semantic Segmentation FSS-1000 (5-shot) DACM (ResNet-101) Mean IoU 91.7 #1 of 22 Archive leaderboard report
Few-Shot Semantic Segmentation FSS-1000 (5-shot) DACM (ResNet-50) Mean IoU 91.6 #2 of 22 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) DACM (VAT, ResNet-101) FB-IoU 79.4 #14 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) DACM (VAT, ResNet-101) Mean IoU 69.1 #14 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) DACM (ResNet-101) FB-IoU 78.9 #25 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) DACM (ResNet-101) Mean IoU 67.5 #25 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) DACM (VAT, ResNet-50) FB-IoU 78.6 #33 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) DACM (VAT, ResNet-50) Mean IoU 66.8 #33 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) DACM (ResNet-50) FB-IoU 77.8 #46 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) DACM (ResNet-50) Mean IoU 65.7 #46 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) DACM (VGG-16) FB-IoU 75.5 #73 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) DACM (VGG-16) Mean IoU 61.8 #73 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) DACM (VAT, ResNet-101) FB-IoU 83.1 #14 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) DACM (VAT, ResNet-101) Mean IoU 73.3 #14 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) DACM (VAT, ResNet-50) FB-IoU 81.7 #23 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) DACM (VAT, ResNet-50) Mean IoU 71.7 #23 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) DACM (ResNet-101) FB-IoU 81.5 #27 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) DACM (ResNet-101) Mean IoU 71.4 #27 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) DACM (ResNet-50) FB-IoU 81.3 #33 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) DACM (ResNet-50) Mean IoU 70.9 #33 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) DACM (VGG-16) FB-IoU 77.8 #72 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) DACM (VGG-16) Mean IoU 65.7 #72 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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