通过匹配高维几何分位数实现模型测试时自适应，兼容各类网络架构。
Matching High-Dimensional Geometric Quantiles for Test-Time Adaptation of Transformers and Convolutional Networks Alike
- 设计可适配任意模型的输入预处理适配器，不修改原模型权重。
- 在CIFAR10-C、CIFAR100-C和TinyImageNet-C上提升分类准确率，最高达+3.8%。
- 理论证明最小化分位数损失可学习最优适配器，适用于卷积与Transformer模型。
测试时自适应（TTA）旨在当测试数据分布与训练数据略有差异时，对分类器进行调整。目前多数方法依赖于特定网络结构来修改模型权重，难以推广至通用架构。本文提出一种无需依赖架构的TTA方法：在输入图像前添加一个适配器网络进行预处理。该适配器通过提出的分位数损失进行训练，不依赖具体模型结构。不同于传统方法，本方法通过匹配高维几何分位数来纠正分布偏移。理论上证明，在合适条件下最小化分位数损失可学习到最优适配器。我们在CIFAR10-C、CIFAR100-C和TinyImageNet-C上验证了该方法，分别在经典卷积网络与Transformer模型上进行了训练，实验结果表明其有效提升了模型鲁棒性。
原文摘要 · Abstract (English)
Test-time adaptation (TTA) refers to adapting a classifier for the test data when the probability distribution of the test data slightly differs from that of the training data of the model. To the best of our knowledge, most of the existing TTA approaches modify the weights of the classifier relying heavily on the architecture. It is unclear as to how these approaches are extendable to generic architectures. In this article, we propose an architecture-agnostic approach to TTA by adding an adapter network pre-processing the input images suitable to the classifier. This adapter is trained using the proposed quantile loss. Unlike existing approaches, we correct for the distribution shift by matching high-dimensional geometric quantiles. We prove theoretically that under suitable conditions minimizing quantile loss can learn the optimal adapter. We validate our approach on CIFAR10-C, CIFAR100-C and TinyImageNet-C by training both classic convolutional and transformer networks on CIFAR10, CIFAR100 and TinyImageNet datasets.
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。