首次评估测试时自适应在真实人脸表情识别中的效果
Evaluating Test-Time Adaptation For Facial Expression Recognition Under Natural Cross-Dataset Distribution Shifts
- 跨数据集实验检验TTA在自然分布偏移下的表现
- 性能提升最高达11.34%，取决于分布距离与噪声程度
- 不同方法适合不同场景，如噪声大或分布差异大
深度学习模型在真实世界部署中常面临自然分布偏移问题。测试时自适应（TTA）通过在推理阶段调整模型，无需标注源数据即可缓解此问题。本文首次对人脸识别表情识别（FER）在自然域偏移下使用TTA方法进行系统评估，采用广泛使用的FER数据集开展跨数据集实验。研究突破了以往合成扰动的局限，聚焦因采集协议、标注标准和人口统计差异导致的真实世界分布变化。结果表明，TTA可使FER性能在自然偏移下提升最高达11.34%。熵最小化方法如TENT和SAR在目标分布较干净时表现最佳；原型调整方法如T3A在分布距离较大时更优；特征对齐方法如SHOT在目标分布噪声更大时带来最大增益。分析显示，TTA有效性由域间分布距离和自然偏移严重程度决定。
原文摘要 · Abstract (English)
Deep learning models often struggle under natural distribution shifts, a common challenge in real-world deployments. Test-Time Adaptation (TTA) addresses this by adapting models during inference without labeled source data. We present the first evaluation of TTA methods for FER under natural domain shifts, performing cross-dataset experiments with widely used FER datasets. This moves beyond synthetic corruptions to examine real-world shifts caused by differing collection protocols, annotation standards, and demographics. Results show TTA can boost FER performance under natural shifts by up to 11.34\%. Entropy minimization methods such as TENT and SAR perform best when the target distribution is clean. In contrast, prototype adjustment methods like T3A excel under larger distributional distance scenarios. Finally, feature alignment methods such as SHOT deliver the largest gains when the target distribution is noisier than our source. Our cross-dataset analysis shows that TTA effectiveness is governed by the distributional distance and the severity of the natural shift across domains.
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。