CRCNet: Few-shot Segmentation with Cross-Reference and Region-Global Conditional Networks
This work addresses the problem of segmenting novel classes with limited training data for computer vision applications, representing an incremental improvement over prior methods.
The paper tackles few-shot segmentation by proposing CRCNet, which uses cross-reference and local-global conditional networks to predict masks for both support and query images, achieving new state-of-the-art performance on datasets like PASCAL VOC 2012, MS COCO, and FSS-1000.
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.