用少量对错反馈实现测试时模型自适应，大幅降低标注成本。
Test-Time Adaptation with Binary Feedback
- 引入二值反馈机制，仅需判断预测对错，减少标注负担。
- 在严重分布偏移下，准确率比顶尖方法提升13.3个百分点。
- 适合标注成本高、数据分布变化大的实际部署场景。
深度学习模型在训练与测试数据存在领域偏移时表现不佳。测试时自适应（TTA）通过仅使用无标签测试样本调整预训练模型来缓解此问题。然而，现有方法在严重领域偏移下失效，而需完整类别标签的主动式TTA因标注成本过高难以应用。为此，本文提出一种新的二值反馈设置：仅需少量标注者提供的二值反馈（判断预测是否正确），显著降低标注负担。在此设定下，提出BiTTA——一种基于强化学习的双路径优化框架，平衡不确定样本上由二值反馈引导的适应与置信预测上的共识自适应。实验表明，BiTTA在严重分布偏移下相比最先进基线提升13.3个百分点准确率，验证了其高效性。代码已公开于https://github.com/taeckyung/BiTTA。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。