Weakly Supervised Segmentation with Maximum Bipartite Graph Matching

By Weide Liu, Chi Zhang, Guosheng Lin, Tzu-Yi Hung, Chunyan Miao. 2020

42 citations recorded by the source corpus.

In the weakly supervised segmentation task with only image-level labels, a common step in many existing algorithms is first to locate the image regions corresponding to each existing class with the Class Activation Maps (CAMs), and then generate the pseudo ground truth masks based on the CAMs to train a segmentation network in the fully supervised manner. The quality of the CAMs has a crucial impact on the performance of the segmentation model. We propose to improve the CAMs from a novel graph perspective. We model paired images containing common classes with a bipartite graph and use the maximum matching algorithm to locate corresponding areas in two images. The matching areas are then used to refine the predicted object regions in the CAMs. The experiments on Pascal VOC 2012 dataset show that our network can effectively boost the performance of the baseline model and achieves new state-of-the-art performance.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Chi Zhang
2. Guosheng Lin
3. Guankai Li
4. Chunhua Shen
5. Bernt Schiele
6. Dacheng Tao
7. Han-Jia Ye
8. Luc Van Gool

Citations in the corpus

• CycleSegNet: Object Co-Segmentation With Cycle Refinement and Region Correspondence (2021, background): “Image cosegmentation algorithms have shown their usages in various computer vision tasks, such as image retrieval [38], 3D reconstruction [29], photo collections [33], image matching [6], [45], [46] and video object tracking and segmentation [23]–[25], [33].”