.png){kind=icon}
返回
Confidence-based and sample-reweighted test-time adaptation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2023.111164.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recently, Test Time Adaptation (TTA) has emerged as a solution to real-world challenges posed by inconsistencies between training and testing distributions. This technique refines a pretrained model for a target domain using only unlabeled test data. However, most existing TTA methods assign equal weights to all samples and are dominated by entropy minimization for adaptation. In this paper, we propose a novel confidence-based optimization strategy and theoretically show that the proposed method tends to yield larger gradients than entropy-based methods and has the potential to enhance performance. Moreover, we show that the importance of samples is frequently underestimated and propose a novel truncation function that assigns an adaptive weight to each sample. The proposed method, named CSTTA, consists of a novel confidence-based optimization strategy and sample-reweighted strategy. It aims to better utilize the sample information for quicker adaptation to new scenarios. Extensive experiments on three digital datasets (CIFAR10-C, CIFAR100-C and ImageNet-C) and a real-world dataset (ImageNet-3DCC) demonstrate the effectiveness of the proposed method.
Keyword:
Deep learning
Test time adaptation
Distribution shift
Robustness
期刊
K
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
分享收藏分享收藏Spatio-Temporal Pattern, Evolution and Influencing Factors of Forest Carbon Sinks in Zhejiang Province, China.png)
Forests
OAAI
ForestsIF0
OAAI分享收藏
查看更多内容