Robust Mean Teacher for Continual and Gradual Test-Time Adaptation
This addresses the challenge of adapting models to sequences of domain shifts during deployment, which is crucial for real-world applications like autonomous driving or medical imaging, though it is incremental as it builds on existing TTA methods.
The paper tackles the problem of continual and gradual test-time adaptation (TTA) by proposing a robust mean teacher method that uses symmetric cross-entropy and contrastive learning to reduce error accumulation, achieving state-of-the-art results on benchmarks like CIFAR10C, CIFAR100C, and Imagenet-C.
Since experiencing domain shifts during test-time is inevitable in practice, test-time adaption (TTA) continues to adapt the model after deployment. Recently, the area of continual and gradual test-time adaptation (TTA) emerged. In contrast to standard TTA, continual TTA considers not only a single domain shift, but a sequence of shifts. Gradual TTA further exploits the property that some shifts evolve gradually over time. Since in both settings long test sequences are present, error accumulation needs to be addressed for methods relying on self-training. In this work, we propose and show that in the setting of TTA, the symmetric cross-entropy is better suited as a consistency loss for mean teachers compared to the commonly used cross-entropy. This is justified by our analysis with respect to the (symmetric) cross-entropy's gradient properties. To pull the test feature space closer to the source domain, where the pre-trained model is well posed, contrastive learning is leveraged. Since applications differ in their requirements, we address several settings, including having source data available and the more challenging source-free setting. We demonstrate the effectiveness of our proposed method 'robust mean teacher' (RMT) on the continual and gradual corruption benchmarks CIFAR10C, CIFAR100C, and Imagenet-C. We further consider ImageNet-R and propose a new continual DomainNet-126 benchmark. State-of-the-art results are achieved on all benchmarks.