Open access
Jul 2026
Adaptive test-time augmentation via KL-regularized reinforcement learning for robust visual inference.
Deep neural networks often suffer significant accuracy degradation when exposed to real-world image corruptions and distribution shifts. To overcome the limitations of fixed, input-agnostic test-time augmentation (TTA), an adaptive framework is proposed that learns per-sample transformations via reinforcement learning....
T. Mittal, A. Dubey, Dharmender Saini et al.
· Scientific Reports · 0 citations