Test-Time Training for Depression Detection
This addresses robustness issues in depression detection for clinical or real-world applications, but it is incremental as it adapts an existing TTT method to a specific domain.
The paper tackles the problem of distribution shifts in depression detection models, which cause severe performance degradation, by applying test-time training (TTT) to improve model robustness, resulting in significant improvements under various shifts such as background noise, gender bias, and dataset differences.
Previous works on depression detection use datasets collected in similar environments to train and test the models. In practice, however, the train and test distributions cannot be guaranteed to be identical. Distribution shifts can be introduced due to variations such as recording environment (e.g., background noise) and demographics (e.g., gender, age, etc). Such distributional shifts can surprisingly lead to severe performance degradation of the depression detection models. In this paper, we analyze the application of test-time training (TTT) to improve robustness of models trained for depression detection. When compared to regular testing of the models, we find TTT can significantly improve the robustness of the model under a variety of distributional shifts introduced due to: (a) background-noise, (b) gender-bias, and (c) data collection and curation procedure (i.e., train and test samples are from separate datasets).