Test-Time Adaptation with Binary Feedback

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lee, Taeckyung, Chottananurak, Sorn, Kim, Junsu, Shin, Jinwoo, Gong, Taesik, Lee, Sung-Ju
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912392296792064
author Lee, Taeckyung
Chottananurak, Sorn
Kim, Junsu
Shin, Jinwoo
Gong, Taesik
Lee, Sung-Ju
author_facet Lee, Taeckyung
Chottananurak, Sorn
Kim, Junsu
Shin, Jinwoo
Gong, Taesik
Lee, Sung-Ju
contents Deep learning models perform poorly when domain shifts exist between training and test data. Test-time adaptation (TTA) is a paradigm to mitigate this issue by adapting pre-trained models using only unlabeled test samples. However, existing TTA methods can fail under severe domain shifts, while recent active TTA approaches requiring full-class labels are impractical due to high labeling costs. To address this issue, we introduce a new setting of TTA with binary feedback. This setting uses a few binary feedback inputs from annotators to indicate whether model predictions are correct, thereby significantly reducing the labeling burden of annotators. Under the setting, we propose BiTTA, a novel dual-path optimization framework that leverages reinforcement learning to balance binary feedback-guided adaptation on uncertain samples with agreement-based self-adaptation on confident predictions. Experiments show BiTTA achieves 13.3%p accuracy improvements over state-of-the-art baselines, demonstrating its effectiveness in handling severe distribution shifts with minimal labeling effort. The source code is available at https://github.com/taeckyung/BiTTA.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18514
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Test-Time Adaptation with Binary Feedback
Lee, Taeckyung
Chottananurak, Sorn
Kim, Junsu
Shin, Jinwoo
Gong, Taesik
Lee, Sung-Ju
Machine Learning
Artificial Intelligence
Deep learning models perform poorly when domain shifts exist between training and test data. Test-time adaptation (TTA) is a paradigm to mitigate this issue by adapting pre-trained models using only unlabeled test samples. However, existing TTA methods can fail under severe domain shifts, while recent active TTA approaches requiring full-class labels are impractical due to high labeling costs. To address this issue, we introduce a new setting of TTA with binary feedback. This setting uses a few binary feedback inputs from annotators to indicate whether model predictions are correct, thereby significantly reducing the labeling burden of annotators. Under the setting, we propose BiTTA, a novel dual-path optimization framework that leverages reinforcement learning to balance binary feedback-guided adaptation on uncertain samples with agreement-based self-adaptation on confident predictions. Experiments show BiTTA achieves 13.3%p accuracy improvements over state-of-the-art baselines, demonstrating its effectiveness in handling severe distribution shifts with minimal labeling effort. The source code is available at https://github.com/taeckyung/BiTTA.
title Test-Time Adaptation with Binary Feedback
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.18514