A Joint Framework Towards Class-aware and Class-agnostic Alignment for Few-shot Segmentation
Abstract
Few-shot segmentation (FSS) aims to segment objects of unseen classes given only a few annotated support images. Most existing methods simply stitch query features with independent support prototypes and segment the query image by feeding the mixed features to a decoder. Although significant improvements have been achieved, existing methods are still face class biases due to class variants and background confusion. In this paper, we propose a joint framework that combines more valuable class-aware and class-agnostic alignment guidance to facilitate the segmentation. Specifically, we design a hybrid alignment module which establishes multi-scale query-support correspondences to mine the most relevant class-aware information for each query image from the corresponding support features. In addition, we explore utilizing base-classes knowledge to generate class-agnostic prior mask which makes a distinction between real background and foreground by highlighting all object regions, especially those of unseen classes. By jointly aggregating class-aware and class-agnostic alignment guidance, better segmentation performances are obtained on query images. Extensive experiments on PASCAL- and COCO- datasets demonstrate that our proposed joint framework performs better, especially on the 1-shot setting.
Cite
@article{arxiv.2211.01310,
title = {A Joint Framework Towards Class-aware and Class-agnostic Alignment for Few-shot Segmentation},
author = {Kai Huang and Mingfei Cheng and Yang Wang and Bochen Wang and Ye Xi and Feigege Wang and Peng Chen},
journal= {arXiv preprint arXiv:2211.01310},
year = {2022}
}