Few-Shot Semantic Segmentation

Follow this topic Ask about this topic

Few-shot semantic segmentation studies how to transfer pixel-level labels from a few support examples to images containing previously unseen classes, reducing the annotation burden for vision tasks. Common approaches compare support and query features using class prototypes, refine predictions with attention or pseudo-labels, or adapt pretrained vision and segmentation models through prompts or lightweight test-time updates. Work spans benchmarks such as PASCAL-5i and COCO-20i as well as cross-domain, remote-sensing, biomedical, and 3D point-cloud settings. A central tension is whether learned adaptation or training-free use of frozen foundation models generalizes better under domain shift while preserving performance on both familiar and novel classes.

Latest papers

32 papers1 paper in the last four weeks, down 80% on the four weeks before. 0.0% of all new papers.

Few to Big: Prototype Expansion Network via Diffusion Learner for Point Cloud Few-shot Semantic Segmentation
Sep 16, 2025Qianguang Zhao, Dongli Wang, Yan Zhou +23D Point Cloud Segmentation Prototype Learning
School of Mathematics and Computational Science, Xiangtan University, Xiangtan 411105, China · School of Automation and Electronics Information, Xiangtan University, Xiangtan 411105, China · School of Automation, Shanghai Jiao Tong University, Shanghai 200232, China
Through the Looking Glass: A Dual Perspective on Weakly-Supervised Few-Shot Segmentation
Aug 22, 2025Jiaqi Ma, Guo-Sen Xie, Fang Zhao +1Weakly Supervised Image Segmentation Weakly Supervised Semantic Segmentation
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China · School of Intelligence Science and Technology, Nanjing University, Suzhou 215163, China

Sep 16, 2025J/K move · Enter open · S save

Few to Big: Prototype Expansion Network via Diffusion Learner for Point Cloud Few-shot Semantic Segmentation

Qianguang Zhao, Dongli Wang, Yan Zhou, Jianxun Li+1

School of Mathematics and Computational Science, Xiangtan University, Xiangtan 411105, China · School of Automation and Electronics Information, Xiangtan University, Xiangtan 411105, China · School of Automation, Shanghai Jiao Tong University, Shanghai 200232, China

3D Point Cloud Segmentation Prototype Learning 3D Semantic Segmentation Few-Shot Semantic Segmentation

Open paper AskPDF arXiv

Few-shot 3D point cloud semantic segmentation aims to segment novel categories using a minimal number of annotated support samples. However, prototypes derived from the limited non-structural point cloud support set are often misaligned and have a small capacity, hindering effective gen eralization to novel categories. This stems from two core issues: i) the prototype possess limited representational capacity fails to cover the full intra-class diversity of a novel category, and ii) the prototypes suffer from misalignment with the query space due to the inter-set inconsistency between support and query sets. To address these issues, our work focuses on leveraging the few support samples to construct a well-aligned big-capacity prototype. Motivated by the powerful generative capabilities of diffusion models, we re-purpose its pre-trained conditional encoder to provide rich feature components for prototype ex pansion. Subsequently, a push-pull force aligns this expanded prototype towards the query feature space. Under this setup, we introduce the Prototype Expansion Network (PENet), a framework that constructs aligned big-capacity prototypes from two complementary feature sources. Specifically, PENet employs a dual-stream learner architecture: it retains a conventional fully supervised Intrinsic Learner (IL) to distill representative features, while introducing a novel Diffusion Learner (DL) to provide rich generalizable features. The resulting dual prototypes are then processed by a Prototype Assimilation Module (PAM), which adopts a push-pull attention block to align the prototypes with the query space. Furthermore, a Prototype Calibration Mechanism (PCM) regularizes the final big-capacity prototype to prevent semantic drift. Extensive experiments on the S3DIS and ScanNet datasets demonstrate that PENet outperforms state-of-the-art methods across various few-shot settings.

Latest papers

Few to Big: Prototype Expansion Network via Diffusion Learner for Point Cloud Few-shot Semantic Segmentation

Through the Looking Glass: A Dual Perspective on Weakly-Supervised Few-Shot Segmentation