NC-TTT: A Noise Contrastive Approach for Test-Time Training
This addresses the issue of domain shift robustness for vision models, representing an incremental improvement in test-time adaptation methods.
The paper tackles the problem of deep learning models struggling with domain shifts during testing by proposing NC-TTT, a novel unsupervised test-time training technique based on discriminating noisy feature maps, which recovers classification performance by an important margin as demonstrated in experiments on several baselines.
Despite their exceptional performance in vision tasks, deep learning models often struggle when faced with domain shifts during testing. Test-Time Training (TTT) methods have recently gained popularity by their ability to enhance the robustness of models through the addition of an auxiliary objective that is jointly optimized with the main task. Being strictly unsupervised, this auxiliary objective is used at test time to adapt the model without any access to labels. In this work, we propose Noise-Contrastive Test-Time Training (NC-TTT), a novel unsupervised TTT technique based on the discrimination of noisy feature maps. By learning to classify noisy views of projected feature maps, and then adapting the model accordingly on new domains, classification performance can be recovered by an important margin. Experiments on several popular test-time adaptation baselines demonstrate the advantages of our method compared to recent approaches for this task. The code can be found at:https://github.com/GustavoVargasHakim/NCTTT.git