ReC-TTT: Contrastive Feature Reconstruction for Test-Time Training
This addresses the challenge of domain adaptation for computer vision models, but it is incremental as it builds on existing test-time training methods.
The paper tackles the problem of adapting deep learning models to real-time variations in data distributions by proposing ReC-TTT, a test-time training technique using contrastive feature reconstruction, which achieves better results than other state-of-the-art methods in most domain shift classification challenges.
The remarkable progress in deep learning (DL) showcases outstanding results in various computer vision tasks. However, adaptation to real-time variations in data distributions remains an important challenge. Test-Time Training (TTT) was proposed as an effective solution to this issue, which increases the generalization ability of trained models by adding an auxiliary task at train time and then using its loss at test time to adapt the model. Inspired by the recent achievements of contrastive representation learning in unsupervised tasks, we propose ReC-TTT, a test-time training technique that can adapt a DL model to new unseen domains by generating discriminative views of the input data. ReC-TTT uses cross-reconstruction as an auxiliary task between a frozen encoder and two trainable encoders, taking advantage of a single shared decoder. This enables, at test time, to adapt the encoders to extract features that will be correctly reconstructed by the decoder that, in this phase, is frozen on the source domain. Experimental results show that ReC-TTT achieves better results than other state-of-the-art techniques in most domain shift classification challenges.