VALSE论文速览 第149期：Robust Test-Time Adaptation in Dynamic Scenarios

论文题目：

Robust Test-Time Adaptation in Dynamic Scenarios

作者列表：

袁龙辉 (北京理工大学)，谢斌辉 (北京理工大学)，李爽 (北京理工大学)

B站观看网址：

https://www.bilibili.com/video/BV1Dg4y197TR/

论文摘要：

Test-time adaptation (TTA) intends to adapt the pretrained model to test distributions with only unlabeled test data streams. Most of the previous TTA methods have achieved great success on simple test data streams such as independently sampled data from single or multiple distributions. However, these attempts may fail in dynamic scenarios of real-world applications like autonomous driving, where the environments gradually change and the test data is sampled correlatively over time. In this work, we explore such practical test data streams to deploy the model on the fly, namely practical test-time adaptation (PTTA). To do so, we elaborate a Robust Test-Time Adaptation (RoTTA) method against the complex data stream in PTTA. More specifically, we present a robust batch normalization scheme to estimate the normalization statistics. Meanwhile, a memory bank is utilized to sample category-balanced data with consideration of timeliness and uncertainty. Further, to stabilize the training procedure, we develop a time-aware reweighting strategy with a teacher-student model. Extensive experiments prove that RoTTA enables continual test-time adaptation on the correlatively sampled data streams. Our method is easy to implement, making it a good choice for rapid deployment.

论文信息：

[1] Longhui Yuan, Binhui Xie, Shuang Li. Robust Test-Time Adaptation in Dynamic Scenarios. CVPR 2023.

视频讲者简介：

袁龙辉，北京理工大学计算机学院硕士生，导师李爽老师，研究兴趣集中在视觉任务上的领域自适应，在CVPR，NeurIPS，AAAI等顶级会议上参与发表多篇论文。

个人主页：

https://yuanlonghui.github.io

特别鸣谢本次论文速览主要组织者：

月度轮值AC：张磊 (重庆大学)

季度轮值AC：张磊 (重庆大学)