Singular Value Penalization and Semantic Data Augmentation for Fully Test-Time Adaptation
원문 초록
Fully test-time adaptation (FTTA) adapts a model that is trained on a source domain to a target domain during the testing phase, where the two domains follow different distributions and source data is unavailable during the training phase. Existing methods usually adopt entropy minimization to reduce the uncertainty of target prediction results, and improve the FTTA performance accordingly. However, they fail to ensure the diversity in target prediction results. Recent domain adaptation study has shown that maximizing the sum of singular values of prediction results can simultaneously enhance their confidence (discriminability) and diversity. However, during the training phase, larger singular values usually take up a dominant position in loss maximization. This results in the model being more inclined to enhance discriminability for easily distinguishable classes, and the improvement in diversity is insufficiently effective. Furthermore, the adaptation and prediction in FTTA only use data from the current batch, which may lead to the risk of overfitting. To address the aforementioned issues, we propose maximizing the sum of singular values while minimizing their variance. This enables the model's focus toward the smaller singular values, enhancing discriminability between more challenging classes and effectively increasing the diversity of prediction results. Moreover, we incorporate data from the previous batch to realize semantic data augmentation for the current batch, reducing the risk of overfitting. Extensive experiments on benchmark datasets show our proposed approach outperforms some compared state-of-the-art FTTA methods.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Speech Quality Assessment Model Based on Mixture of Experts: System-Level Performance Enhancement and Utterance-Level Challenge Analysis
orGAN: A Synthetic Data Augmentation Pipeline for Simultaneous Generation of Surgical Images and Ground Truth Labels
M2BeamLLM: Multimodal Sensing-empowered mmWave Beam Prediction with Large Language Models
A Multi-Agent Probabilistic Inference Framework Inspired by Kairanban-Style CoT System with IdoBata Conversation for Debiasing
Long Term Stock Prediction based on Financial Statements
SenseShift6D: Multimodal RGB-D Benchmarking for Robust 6D Pose Estimation across Environment and Sensor Variations
토론
이 논문과 연결된 포럼 글이 아직 없습니다.