ReC-TTT: Contrastive Feature Reconstruction for Test-Time Training

TL;DR

ReC-TTT introduces a contrastive feature reconstruction method for test-time training that enhances model adaptation to unseen domains by generating discriminative views and utilizing cross-reconstruction with shared decoders.

Contribution

It proposes a novel contrastive test-time training approach using cross-reconstruction with shared decoders to improve domain adaptation in deep learning models.

Findings

ReC-TTT outperforms state-of-the-art methods in domain shift classification tasks.

The method effectively adapts models to unseen data distributions.

Experimental results demonstrate improved generalization in real-time variations.

Abstract

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.