Papers › Applying ViT in Generalized Few-shot Semantic Segmentation

Applying ViT in Generalized Few-shot Semantic Segmentation

27 Aug 2024arXiv:2408.14957archive 2025-07-28

Liyuan Geng, Jinhong Xia, Yuanhe Guo

This paper explores the capability of ViT-based models under the generalized few-shot semantic segmentation (GFSS) framework. We conduct experiments with various combinations of backbone models, including ResNets and pretrained Vision Transformer (ViT)-based models, along with decoders featuring a linear classifier, UPerNet, and Mask Transformer. The structure made of DINOv2 and linear classifier takes the lead on popular few-shot segmentation bench mark PASCAL-5ⁱ, substantially outperforming the best of ResNet structure by 116% in one-shot scenario. We demonstrate the great potential of large pretrained ViT-based model on GFSS task, and expect further improvement on testing benchmarks. However, a potential caveat is that when applying pure ViT-based model and large scale ViT decoder, the model is easy to overfit.

PaperPDFCode

Code

lgnyu/vitseg 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

DecoderFew-Shot Semantic SegmentationGeneralized Few-Shot Semantic SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionAverage PoolingBPEConvolutionDense ConnectionsDropoutGlobal Average PoolingKaiming InitializationLabel SmoothingLayer NormalizationLinear LayerMax PoolingMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerVision Transformer

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