Papers › A Surprisingly Simple Approach to Generalized Few-Shot Semantic Segmentation

A Surprisingly Simple Approach to Generalized Few-Shot Semantic Segmentation

26 Sep 2024NeurIPS 2024 9archive 2025-07-28

Tomoya Sakai, Haoxiang Qiu, Takayuki Katsuki, Daiki Kimura, Takayuki Osogami, Tadanobu Inoue

The goal of generalized few-shot semantic segmentation (GFSS) is to recognize novel-class objects through training with a few annotated examples and the base-class model that learned the knowledge about the base classes. Unlike the classic few-shot semantic segmentation, GFSS aims to classify pixels into both base and novel classes, meaning it is a more practical setting. Current GFSS methods rely on several techniques such as using combinations of customized modules, carefully designed loss functions, meta-learning, and transductive learning. However, we found that a simple rule and standard supervised learning substantially improve the GFSS performance. In this paper, we propose a simple yet effective method for GFSS that does not use the techniques mentioned above. Also, we theoretically show that our method perfectly maintains the segmentation performance of the base-class model over most of the base classes. Through numerical experiments, we demonstrated the effectiveness of our method. It improved in novel-class segmentation performance in the 1-shot scenario by 6.1% on the PASCAL-5ⁱ dataset, 4.7% on the PASCAL-10ⁱ dataset, and 1.0% on the COCO-20ⁱ dataset.

PaperPDFCode

Syntology This paper has no arXiv id in the archive, and this site joins papers to Syntology's graph by arXiv id, so this page does not say whether the graph holds it.

Code

IBM/BCM officialpytorchSyntology: not harvested 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 SegmentationInductive LearningSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Generalized Few-Shot Semantic Segmentation COCO-20i (1-shot) BCM (ResNet-50) Mean Base and Novel 33.85 #3 of 6 Archive leaderboard report
Generalized Few-Shot Semantic Segmentation COCO-20i (5-shot) BCM (ResNet-50) Mean Base and Novel 40.24 #3 of 5 Archive leaderboard report
Generalized Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) BCM (ResNet-50) Mean Base and Novel 56.20 #2 of 5 Archive leaderboard report
Generalized Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) BCM (ResNet-50) Mean Base and Novel 63.29 #3 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 PoolingBASEBatch NormalizationConvolutionDilated ConvolutionLogistic RegressionPSPNetPyramid 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