VALSE 论文速览 第110期：Towards Fewer Annotations

论文题目：Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation

作者列表：谢斌辉 (北理工)、袁龙辉 (北理工)、李爽 (北理工)、刘驰 (北理工)、程新景 (嬴彻科技)

B站观看网址：

https://www.bilibili.com/video/BV1Xo4y1j7KR/

论文摘要：

Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively generates pseudo labels on unlabeled target data and retrains the network. However, realistic segmentation datasets are highly imbalanced, pseudo labels are typically biased to the majority classes and basically noisy, leading to an error-prone and suboptimal model. In this paper, we propose a simple region-based active learning approach for semantic segmentation under a domain shift, aiming to automatically query a small partition of image regions to be labeled while maximizing segmentation performance. Our algorithm, Region Impurity and Prediction Uncertainty (RIPU), introduces a new acquisition strategy characterizing the spatial adjacency of image regions along with the prediction confidence. We show that the proposed region-based selection strategy makes more efficient use of a limited budget than image-based or point-based counterparts. Further, we enforce local prediction consistency between a pixel and its nearest neighbors on a source image. Alongside this, we develop a negative learning loss to make the features more discriminative. Extensive experiments demonstrate that our method only requires very few annotations to almost reach the supervised performance and substantially outperforms state-of-the-art methods.

论文信息：

[1] Binhui Xie, Longhui Yuan, Shuang Li, Chi Harold Liu, Xinjing Cheng. Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation. CVPR 2022: 8058-8068.

论文链接：

[https://arxiv.org/abs/2111.12940]

代码链接：

[https://github.com/BIT-DA/RIPU]

视频讲者简介：

谢斌辉，北京理工大学计算机学院博士生，导师李爽老师。研究兴趣集中在视觉任务中的领域适应、主动学习和自监督学习。在T-PAMI、TKDE、CVPR、AAAI等顶级期刊和会议发表多篇论文，担任多个学术会议和期刊的审稿人 (TPAMI、ICLR、CVPR、ICCV、ECCV、AAAI等)。

特别鸣谢本次论文速览主要组织者：

月度轮值AC：林迪 (天津大学)、郑乾 (浙江大学)