Open-World Test-Time Training: Self-Training with Contrast Learning
This addresses domain generalization for deep learning models in real-world applications with unknown distributions, though it appears incremental as it builds on existing test-time training methods.
The paper tackles the problem of test-time training in open-world scenarios with strong out-of-distribution data, introducing Open World Dynamic Contrastive Learning (OWDCL) to enhance early-stage feature extraction and robustness, achieving state-of-the-art performance on comparison datasets.
Traditional test-time training (TTT) methods, while addressing domain shifts, often assume a consistent class set, limiting their applicability in real-world scenarios characterized by infinite variety. Open-World Test-Time Training (OWTTT) addresses the challenge of generalizing deep learning models to unknown target domain distributions, especially in the presence of strong Out-of-Distribution (OOD) data. Existing TTT methods often struggle to maintain performance when confronted with strong OOD data. In OWTTT, the focus has predominantly been on distinguishing between overall strong and weak OOD data. However, during the early stages of TTT, initial feature extraction is hampered by interference from strong OOD and corruptions, resulting in diminished contrast and premature classification of certain classes as strong OOD. To address this, we introduce Open World Dynamic Contrastive Learning (OWDCL), an innovative approach that utilizes contrastive learning to augment positive sample pairs. This strategy not only bolsters contrast in the early stages but also significantly enhances model robustness in subsequent stages. In comparison datasets, our OWDCL model has produced the most advanced performance.