Papers › A Strong Baseline for Generalized Few-Shot Semantic Segmentation

A Strong Baseline for Generalized Few-Shot Semantic Segmentation

25 Nov 2022CVPR 2023 1arXiv:2211.14126archive 2025-07-28

Sina Hajimiri, Malik Boudiaf, Ismail Ben Ayed, Jose Dolz

This paper introduces a generalized few-shot segmentation framework with a straightforward training process and an easy-to-optimize inference phase. In particular, we propose a simple yet effective model based on the well-known InfoMax principle, where the Mutual Information (MI) between the learned feature representations and their corresponding predictions is maximized. In addition, the terms derived from our MI-based formulation are coupled with a knowledge distillation term to retain the knowledge on base classes. With a simple training process, our inference model can be applied on top of any segmentation network trained on base classes. The proposed inference yields substantial improvements on the popular few-shot segmentation benchmarks, PASCAL-5ⁱ and COCO-20ⁱ. Particularly, for novel classes, the improvement gains range from 7% to 26% (PASCAL-5ⁱ) and from 3% to 12% (COCO-20ⁱ) in the 1-shot and 5-shot scenarios, respectively. Furthermore, we propose a more challenging setting, where performance gaps are further exacerbated. Our code is publicly available at https://github.com/sinahmr/DIaM.

PaperPDFConference PDFCode

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

Code

sinahmr/diam officialmentioned in papermentioned on GitHubpytorchMIT report
cliffbb/oem-fewshot-challenge mentioned 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

Few-Shot Semantic SegmentationGeneralized Few-Shot Semantic SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Generalized Few-Shot Semantic Segmentation COCO-20i (1-shot) DIaM (ResNet-50) Mean Base and Novel 32.75 #4 of 6 Archive leaderboard report
Generalized Few-Shot Semantic Segmentation COCO-20i (1-shot) DIaM (ResNet-50) Mean IoU 40.52 #4 of 6 Archive leaderboard report
Generalized Few-Shot Semantic Segmentation COCO-20i (5-shot) DIaM (ResNet-50) Mean Base and Novel 38.55 #4 of 5 Archive leaderboard report
Generalized Few-Shot Semantic Segmentation COCO-20i (5-shot) DIaM (ResNet-50) Mean IoU 43.46 #4 of 5 Archive leaderboard report
Generalized Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) DIaM (ResNet-50) Mean Base and Novel 53 #4 of 5 Archive leaderboard report
Generalized Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) DIaM (ResNet-50) Mean IoU 61.95 #4 of 5 Archive leaderboard report
Generalized Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) DIaM (ResNet-50) Mean Base and Novel 63.08 #4 of 6 Archive leaderboard report
Generalized Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) DIaM (ResNet-50) Mean IoU 66.97 #4 of 6 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

Auxiliary ClassifierAverage PoolingBatch NormalizationConvolutionDilated ConvolutionKnowledge DistillationPSPNetPyramid Pooling ModuleReLU

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