arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.10792cs.CVcs.AI
收藏

基于最近邻信息的自训练测试时自适应

Test-Time Adaptation via Self-Training with Nearest Neighbor Information

Korea Advanced Institute of Science and Technology(韩国科学技术院)

Minguk Jang, Sae-Young Chung, Hye Won Chung

摘要:

测试时自适应(Test-time adaptation,TTA)的目标是仅使用在线未标记的测试数据,而不需要任何与训练过程相关的信息来调整已训练的分类器。大多数现有的TTA方法使用分类器对测试数据的预测作为伪标签来适应训练的分类器。然而,在测试时域移位下,伪标签的准确性不能得到保证,因此TTA方法经常在自适应分类器处遇到性能下降。为了克服这一缺陷,本文提出了一种新的测试时自适应方法--基于最近邻信息的自训练测试时自适应(Test-time Adaptation via Self-Training with Nearest Neighbor Information,TAST),该方法包括以下步骤:(1)在训练好的特征提取器上增加可训练的自适应模块;(3)在测试时间期间仅训练这些模块几次,以匹配测试数据的基于最近邻的伪标签分布和基于原型的类分布;以及(4)使用来自这些模块的平均预测类分布来预测测试数据的标签。伪标签生成基于以下基本直觉:在域移位下,测试数据及其在嵌入空间中的最近邻居可能共享相同的标签。通过利用多个随机初始化的自适应模块,TAST提取有用的信息的分类下的域移位的测试数据,使用最近的邻居信息。TAST在两个标准的基准任务上表现出比最先进的TTA方法更好的性能,即领域泛化,即VLCS,PACS,TASTHome和TerraIncognita,以及图像损坏,特别是CIFAR-10/100 C。

英文摘要:

Test-time adaptation (TTA) aims to adapt a trained classifier using online unlabeled test data only, without any information related to the training procedure. Most existing TTA methods adapt the trained classifier using the classifier's prediction on the test data as pseudo-label. However, under test-time domain shift, accuracy of the pseudo labels cannot be guaranteed, and thus the TTA methods often encounter performance degradation at the adapted classifier. To overcome this limitation, we propose a novel test-time adaptation method, called Test-time Adaptation via Self-Training with nearest neighbor information (TAST), which is composed of the following procedures: (1) adds trainable adaptation modules on top of the trained feature extractor; (2) newly defines a pseudo-label distribution for the test data by using the nearest neighbor information; (3) trains these modules only a few times during test time to match the nearest neighbor-based pseudo label distribution and a prototype-based class distribution for the test data; and (4) predicts the label of test data using the average predicted class distribution from these modules. The pseudo-label generation is based on the basic intuition that a test data and its nearest neighbor in the embedding space are likely to share the same label under the domain shift. By utilizing multiple randomly initialized adaptation modules, TAST extracts useful information for the classification of the test data under the domain shift, using the nearest neighbor information. TAST showed better performance than the state-of-the-art TTA methods on two standard benchmark tasks, domain generalization, namely VLCS, PACS, OfficeHome, and TerraIncognita, and image corruption, particularly CIFAR-10/100C.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑