CRCNet: Few-shot Segmentation with Cross-Reference and Region-Global Conditional Networks

TL;DR

CRCNet introduces a novel few-shot segmentation approach that uses cross-reference and local-global conditional modules to improve co-occurrent object detection and achieve state-of-the-art results on multiple datasets.

Contribution

The paper proposes CRCNet, which concurrently predicts masks for support and query images and incorporates cross-reference and local-global modules for enhanced feature comparison.

Findings

Achieves state-of-the-art performance on PASCAL VOC 2012.

Outperforms previous methods on MS COCO and FSS-1000 datasets.

Demonstrates effective co-occurrent object detection in few-shot segmentation.

Abstract

Few-shot segmentation aims to learn a segmentation model that can be generalized to novel classes with only a few training images. In this paper, we propose a Cross-Reference and Local-Global Conditional Networks (CRCNet) for few-shot segmentation. Unlike previous works that only predict the query image's mask, our proposed model concurrently makes predictions for both the support image and the query image. Our network can better find the co-occurrent objects in the two images with a cross-reference mechanism, thus helping the few-shot segmentation task. To further improve feature comparison, we develop a local-global conditional module to capture both global and local relations. We also develop a mask refinement module to refine the prediction of the foreground regions recurrently. Experiments on the PASCAL VOC 2012, MS COCO, and FSS-1000 datasets show that our network achieves new state-of-the-art performance.