CRNet(Cross-Reference Networks)[1] make predictions for both the support image and the query image. It can better find the co-occurrent objects in the two images, thus helping the few-shot segmentation task. There are some details of reading and implementing it.

Contents

• Paper & Code & note
• Paper understanding
• Code understanding
• Note
• References

Paper & Code & note

Paper: CRNet: Cross-Reference Networks for Few-Shot Segmentation(CVPR 2020 paper)
Code: [Code]
Note: Mendeley

Paper

Abstract

1. Image segmentation algorithms are based on deep convolutional neural networks in recent years.
2. Few-shot segmentation aims to learn a segmentation model that can be gener- alized to novel classes with only a few training images.
3. In this work, they propose a cross-reference network (CRNet) including cross-reference module for finding the co-occurrent objects and mask refinement module for refining predictions.
4. It achieves state-of-the-art performance on the PASCAL VOC 2012 dataset.

Problem Description

Problem Solution

Conceptual Understanding

Core Conception

Experiments

Code

[Updating]

Note

[Updating]

References

[1] Liu W, Zhang C, Lin G, et al. CRNet: Cross-Reference Networks for Few-Shot Segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 4165-4173.