Learning Superpixels with Segmentation-Aware Affinity Loss

Wei-Chih Tu1, Ming-Yu Liu2, Varun Jampani2, Deqing Sun2, Shao-Yi Chien1, Ming-Hsuan Yang2, 3, Jan Kautz2

1National Taiwan University, 2NVIDIA, 3UC Merced

Illustration of the proposed segmentation-aware affinity learning framework for superpixels

Abstract

Superpixel segmentation has been widely used in many computer vision tasks. Existing superpixel algorithms are mainly based on hand-crafted features, which often fail to preserve weak object boundaries. In this work, we leverage deep neural networks to facilitate extracting superpixels from images. We show a simple integration of deep features with existing superpixel algorithms does not result in better performance as these features do not model segmentation. Instead, we propose a segmentation-aware affinity learning approach for superpixel segmentation. Specifically, we propose a new loss function that takes the segmentation error into account for affinity learning. We also develop the Pixel Affinity Net for affinity prediction. Extensive experimental results show that the proposed algorithm based on the learned segmentation-aware loss performs favorably against the state-of-the-art methods. We also demonstrate the use of the learned superpixels in numerous vision applications with consistent improvements.

Downloads


Bibtex

@inproceedings{Tu-CVPR-2018,
    author = {Tu, Wei-Chih and Liu, Ming-Yu and Jampani, Varun and Sun, Deqing and Chien, Shao-Yi and Yang, Ming-Hsuan and Kautz, Jan},
    title = {Learning Superpixels with Segmentation-Aware Affinity Loss},
    booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    month = {June},
    year = {2018},
}