CobNet: Cross Attention on Object and Background for Few-Shot Segmentation

TL;DR

CobNet introduces a novel approach for few-shot segmentation that leverages query image background information without annotations, significantly improving performance on standard benchmarks.

Contribution

The paper proposes CobNet, a method that utilizes query image background information for few-shot segmentation, addressing limitations of previous background extraction techniques.

Findings

Achieves 61.4% mIoU on PASCAL-5i for 1-shot segmentation.

Achieves 37.8% mIoU on COCO-20i for 1-shot segmentation.

State-of-the-art 53.7% performance in weakly-supervised few-shot segmentation.

Abstract

Few-shot segmentation aims to segment images containing objects from previously unseen classes using only a few annotated samples. Most current methods focus on using object information extracted, with the aid of human annotations, from support images to identify the same objects in new query images. However, background information can also be useful to distinguish objects from their surroundings. Hence, some previous methods also extract background information from the support images. In this paper, we argue that such information is of limited utility, as the background in different images can vary widely. To overcome this issue, we propose CobNet which utilises information about the background that is extracted from the query images without annotations of those images. Experiments show that our method achieves a mean Intersection-over-Union score of 61.4% and 37.8% for 1-shot segmentation on PASCAL-5i and COCO-20i respectively, outperforming previous methods. It is also shown to produce state-of-the-art performances of 53.7% for weakly-supervised few-shot segmentation, where no annotations are provided for the support images.