CRNet : cross-reference networks for few-shot segmentation

• Main Authors: Liu, Weide, Zhang, Chi, Lin, Guosheng, Liu, Fayao
• 其他作者: School of Computer Science and Engineering
• 格式: Conference or Workshop Item
• 語言: English
• 出版: 2020
• 主題: Engineering::Computer science and engineering; Image Segmentation; Predictive Models
• 在線閱讀: https://hdl.handle.net/10356/144247
• 機構: Nanyang Technological University

Over the past few years, state-of-the-art image segmentation algorithms are based on deep convolutional neural networks. To render a deep network with the ability to understand a concept, humans need to collect a large amount of pixel-level annotated data to train the models, which is time-consuming and tedious. Recently, few-shot segmentation is proposed to solve this problem. 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 network (CRNet) for few-shot segmentation. Unlike previous works which only predict the mask in the query image, our proposed model concurrently make predictions for both the support image and the query image. With a cross-reference mechanism, our network can better find the co-occurrent objects in the two images, thus helping the few-shot segmentation task. We also develop a mask refinement module to recurrently refine the prediction of the foreground regions. For the k-shot learning, we propose to finetune parts of networks to take advantage of multiple labeled support images. Experiments on the PASCAL VOC 2012 dataset show that our network achieves state-of-the-art performance.