English

Masked Cross-image Encoding for Few-shot Segmentation

Computer Vision and Pattern Recognition 2023-08-23 v1

Abstract

Few-shot segmentation (FSS) is a dense prediction task that aims to infer the pixel-wise labels of unseen classes using only a limited number of annotated images. The key challenge in FSS is to classify the labels of query pixels using class prototypes learned from the few labeled support exemplars. Prior approaches to FSS have typically focused on learning class-wise descriptors independently from support images, thereby ignoring the rich contextual information and mutual dependencies among support-query features. To address this limitation, we propose a joint learning method termed Masked Cross-Image Encoding (MCE), which is designed to capture common visual properties that describe object details and to learn bidirectional inter-image dependencies that enhance feature interaction. MCE is more than a visual representation enrichment module; it also considers cross-image mutual dependencies and implicit guidance. Experiments on FSS benchmarks PASCAL-5i5^i and COCO-20i20^i demonstrate the advanced meta-learning ability of the proposed method.

Keywords

Cite

@article{arxiv.2308.11201,
  title  = {Masked Cross-image Encoding for Few-shot Segmentation},
  author = {Wenbo Xu and Huaxi Huang and Ming Cheng and Litao Yu and Qiang Wu and Jian Zhang},
  journal= {arXiv preprint arXiv:2308.11201},
  year   = {2023}
}

Comments

conference

R2 v1 2026-06-28T12:01:07.569Z