DeepCO3: Deep Instance Co-Segmentation by Co-Peak Search and Co-Saliency Detection

Kuang-Jui Hsu, Yen-Yu Lin, Yung-Yu Chuang; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 8846-8855

Abstract


In this paper, we address a new task called instance co-segmentation. Given a set of images jointly covering object instances of a specific category, instance co-segmentation aims to identify all of these instances and segment each of them, i.e. generating one mask for each instance. This task is important since instance-level segmentation is preferable for humans and many vision applications. It is also challenging because no pixel-wise annotated training data are available and the number of instances in each image is unknown. We solve this task by dividing it into two sub-tasks, co-peak search and instance mask segmentation. In the former sub-task, we develop a CNN-based network to detect the co-peaks as well as co-saliency maps for a pair of images. A co-peak has two endpoints, one in each image, that are local maxima in the response maps and similar to each other. Thereby, the two endpoints are potentially covered by a pair of instances of the same category. In the latter subtask, we design a ranking function that takes the detected co-peaks and co-saliency maps as inputs and can select the object proposals to produce the final results. Our method for instance co-segmentation and its variant for object colocalization are evaluated on four datasets, and achieve favorable performance against the state-of-the-art methods. The source codes and the collected datasets are available at https://github.com/KuangJuiHsu/DeepCO3/

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Hsu_2019_CVPR,
author = {Hsu, Kuang-Jui and Lin, Yen-Yu and Chuang, Yung-Yu},
title = {DeepCO3: Deep Instance Co-Segmentation by Co-Peak Search and Co-Saliency Detection},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}