Papers › Iterative Few-shot Semantic Segmentation from Image Label Text

Iterative Few-shot Semantic Segmentation from Image Label Text

10 Mar 2023arXiv:2303.05646archive 2025-07-28

Haohan Wang, Liang Liu, Wuhao Zhang, Jiangning Zhang, Zhenye Gan, Yabiao Wang, Chengjie Wang, Haoqian Wang

Few-shot semantic segmentation aims to learn to segment unseen class objects with the guidance of only a few support images. Most previous methods rely on the pixel-level label of support images. In this paper, we focus on a more challenging setting, in which only the image-level labels are available. We propose a general framework to firstly generate coarse masks with the help of the powerful vision-language model CLIP, and then iteratively and mutually refine the mask predictions of support and query images. Extensive experiments on PASCAL-5i and COCO-20i datasets demonstrate that our method not only outperforms the state-of-the-art weakly supervised approaches by a significant margin, but also achieves comparable or better results to recent supervised methods. Moreover, our method owns an excellent generalization ability for the images in the wild and uncommon classes. Code will be available at https://github.com/Whileherham/IMR-HSNet.

PaperPDFCode

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

Code

whileherham/imr-hsnet 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

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

Tasks

Few-Shot Semantic SegmentationLanguage ModelingLanguage ModellingSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Semantic Segmentation COCO-20i (1-shot) IMR-HSNet (ResNet-50) Mean IoU 42.4 #49 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) IIMR-HSNet (VGG-16) Mean IoU 37.7 #67 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) IMR-HSNet (ResNet-50) Mean IoU 44.4 #63 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) IMR-HSNet (ResNet-50) Mean IoU 61.1 #76 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) IMR-HSNet (VGG-16) Mean IoU 56.5 #94 of 105 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

CLIP

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