Acquiring the most representative examples via active learning (AL) can benefit many data-dependent computer vision tasks by minimizing efforts of image-level or pixel-wise annotations. In this paper, we propose a novel Collaborative Panoptic-Regional Active Learning framework (CPRAL) to address the semantic segmentation task. For a small batch of images initially sampled with pixel-wise annotations, we employ panoptic information to initially select unlabeled samples. Considering the class imbalance in the segmentation dataset, we import a Regional Gaussian Attention module (RGA) to achieve semantics-biased selection. The subset is highlighted by vote entropy and then attended by Gaussian kernels to maximize the biased regions. We also propose a Contextual Labels Extension (CLE) to boost regional annotations with contextual attention guidance. With the collaboration of semantics-agnostic panoptic matching and regionbiased selection and extension, our CPRAL can strike a balance between labeling efforts and performance and compromise the semantics distribution. We perform extensive experiments on Cityscapes and BDD10K datasets and show that CPRAL outperforms the cutting-edge methods with impressive results and less labeling proportion.
@article{arxiv.2112.05975,
title = {CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation},
author = {Yu Qiao and Jincheng Zhu and Chengjiang Long and Zeyao Zhang and Yuxin Wang and Zhenjun Du and Xin Yang},
journal= {arXiv preprint arXiv:2112.05975},
year = {2022}
}
Comments
This is not the final version of our paper, and we will upload a final version later