ClusT3: Information Invariant Test-Time Training
This addresses domain shift vulnerabilities in vision tasks, but appears incremental as it builds on existing test-time training methods.
The paper tackles the problem of deep learning models being vulnerable to domain shifts at test-time by proposing ClusT3, a novel unsupervised test-time training technique based on maximizing mutual information between multi-scale feature maps and a discrete latent representation. The result is competitive classification performance on popular test-time adaptation benchmarks.
Deep Learning models have shown remarkable performance in a broad range of vision tasks. However, they are often vulnerable against domain shifts at test-time. Test-time training (TTT) methods have been developed in an attempt to mitigate these vulnerabilities, where a secondary task is solved at training time simultaneously with the main task, to be later used as an self-supervised proxy task at test-time. In this work, we propose a novel unsupervised TTT technique based on the maximization of Mutual Information between multi-scale feature maps and a discrete latent representation, which can be integrated to the standard training as an auxiliary clustering task. Experimental results demonstrate competitive classification performance on different popular test-time adaptation benchmarks.