Papers › Integrative Few-Shot Learning for Classification and Segmentation

Integrative Few-Shot Learning for Classification and Segmentation

29 Mar 2022CVPR 2022 1arXiv:2203.15712archive 2025-07-28

Dahyun Kang, Minsu Cho

We introduce the integrative task of few-shot classification and segmentation (FS-CS) that aims to both classify and segment target objects in a query image when the target classes are given with a few examples. This task combines two conventional few-shot learning problems, few-shot classification and segmentation. FS-CS generalizes them to more realistic episodes with arbitrary image pairs, where each target class may or may not be present in the query. To address the task, we propose the integrative few-shot learning (iFSL) framework for FS-CS, which trains a learner to construct class-wise foreground maps for multi-label classification and pixel-wise segmentation. We also develop an effective iFSL model, attentive squeeze network (ASNet), that leverages deep semantic correlation and global self-attention to produce reliable foreground maps. In experiments, the proposed method shows promising performance on the FS-CS task and also achieves the state of the art on standard few-shot segmentation benchmarks.

PaperPDFConference PDFCode

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

Code

dahyun-kang/ifsl officialmentioned in papermentioned on GitHubpytorch 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

ClassificationFew-Shot LearningFew-Shot Semantic SegmentationMUlTI-LABEL-ClASSIFICATIONMulti-Label ClassificationSegmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Semantic Segmentation COCO-20i (1-shot) ASNet Mean IoU 43.1 #45 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) ASNet Mean IoU 49.5 #41 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) ASNet Mean IoU 66.9 #32 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) ASNet Mean IoU 71.1 #30 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

AttentionDense ConnectionsLinear 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