Gradient Alignment with Prototype Feature for Fully Test-time Adaptation
원문 초록
In context of Test-time Adaptation(TTA), we propose a regularizer, dubbed Gradient Alignment with Prototype feature (GAP), which alleviates the inappropriate guidance from entropy minimization loss from misclassified pseudo label. We developed a gradient alignment loss to precisely manage the adaptation process, ensuring that changes made for some data don't negatively impact the model's performance on other data. We introduce a prototype feature of a class as a proxy measure of the negative impact. To make GAP regularizer feasible under the TTA constraints, where model can only access test data without labels, we tailored its formula in two ways: approximating prototype features with weight vectors of the classifier, calculating gradient without back-propagation. We demonstrate GAP significantly improves TTA methods across various datasets, which proves its versatility and effectiveness.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models
Bridging the Gap for Test-Time Multimodal Sentiment Analysis
ETAGE: Enhanced Test Time Adaptation with Integrated Entropy and Gradient Norms for Robust Model Performance
Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation
Analytic Continual Test-Time Adaptation for Multi-Modality Corruption
Enhancing Test Time Adaptation with Few-shot Guidance
토론
이 논문과 연결된 포럼 글이 아직 없습니다.