Test-Time Training for Depression Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911830176169984 |
|---|---|
| author | Dumpala, Sri Harsha Sastry, Chandramouli Shama Uher, Rudolf Oore, Sageev |
| author_facet | Dumpala, Sri Harsha Sastry, Chandramouli Shama Uher, Rudolf Oore, Sageev |
| contents | 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). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_05071 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Test-Time Training for Depression Detection Dumpala, Sri Harsha Sastry, Chandramouli Shama Uher, Rudolf Oore, Sageev Machine Learning Sound Audio and Speech Processing 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). |
| title | Test-Time Training for Depression Detection |
| topic | Machine Learning Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2404.05071 |