ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2111.12263
14
32

APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation

24 November 2021
Jiacheng Chen
Bin-Bin Gao
Zongqing Lu
Jing-Hao Xue
Chengjie Wang
Q. Liao
    VLM
ArXivPDFHTML
Abstract

Few-shot semantic segmentation aims to segment novel-class objects in a given query image with only a few labeled support images. Most advanced solutions exploit a metric learning framework that performs segmentation through matching each query feature to a learned class-specific prototype. However, this framework suffers from biased classification due to incomplete feature comparisons. To address this issue, we present an adaptive prototype representation by introducing class-specific and class-agnostic prototypes and thus construct complete sample pairs for learning semantic alignment with query features. The complementary features learning manner effectively enriches feature comparison and helps yield an unbiased segmentation model in the few-shot setting. It is implemented with a two-branch end-to-end network (i.e., a class-specific branch and a class-agnostic branch), which generates prototypes and then combines query features to perform comparisons. In addition, the proposed class-agnostic branch is simple yet effective. In practice, it can adaptively generate multiple class-agnostic prototypes for query images and learn feature alignment in a self-contrastive manner. Extensive experiments on PASCAL-5i^ii and COCO-20i^ii demonstrate the superiority of our method. At no expense of inference efficiency, our model achieves state-of-the-art results in both 1-shot and 5-shot settings for semantic segmentation.

View on arXiv
Comments on this paper