Papers › Cost Aggregation Is All You Need for Few-Shot Segmentation

Cost Aggregation Is All You Need for Few-Shot Segmentation

22 Dec 2021arXiv:2112.11685archive 2025-07-28

Sunghwan Hong, Seokju Cho, Jisu Nam, Seungryong Kim

We introduce a novel cost aggregation network, dubbed Volumetric Aggregation with Transformers (VAT), to tackle the few-shot segmentation task by using both convolutions and transformers to efficiently handle high dimensional correlation maps between query and support. In specific, we propose our encoder consisting of volume embedding module to not only transform the correlation maps into more tractable size but also inject some convolutional inductive bias and volumetric transformer module for the cost aggregation. Our encoder has a pyramidal structure to let the coarser level aggregation to guide the finer level and enforce to learn complementary matching scores. We then feed the output into our affinity-aware decoder along with the projected feature maps for guiding the segmentation process. Combining these components, we conduct experiments to demonstrate the effectiveness of the proposed method, and our method sets a new state-of-the-art for all the standard benchmarks in few-shot segmentation task. Furthermore, we find that the proposed method attains state-of-the-art performance even for the standard benchmarks in semantic correspondence task although not specifically designed for this task. We also provide an extensive ablation study to validate our architectural choices. The trained weights and codes are available at: https://seokju-cho.github.io/VAT/.

PaperPDFCode

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

Code

Seokju-Cho/Volumetric-Aggregation-Transformer officialmentioned on GitHubpytorch report
SunghwanHong/Cost-Aggregation-transformers mentioned on GitHubpytorchGPL-3.0 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

AllDecoderFew-Shot Semantic SegmentationInductive BiasSegmentationSemantic correspondence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Semantic Segmentation COCO-20i (1-shot) VAT (ResNet-50) Mean IoU 41.3 #59 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) VAT (ResNet-50) Mean IoU 47.9 #52 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation FSS-1000 (1-shot) VAT Mean IoU 90.0 #8 of 24 Archive leaderboard report
Few-Shot Semantic Segmentation FSS-1000 (5-shot) VAT Mean IoU 90.6 #5 of 22 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) VAT Mean IoU 67.5 #26 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) VAT Mean IoU 71.6 #24 of 96 Archive leaderboard report
Semantic correspondence PF-PASCAL VAT PCK 92.3 #7 of 15 Archive leaderboard report
Semantic correspondence PF-WILLOW VAT PCK 81.0 #3 of 8 Archive leaderboard report
Semantic correspondence SPair-71k VAT PCK 54.2 #13 of 22 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