3 papers
cs.CV2026
Can We Change the Stroke Size for Easier Diffusion?
Yunwei Bai, Ying Kiat Tan, Yao Shu +1
Diffusion models can be challenged in the low signal-to-noise regime, where they have to make pixel-level predictions despite the presence of high noise. The geometric intuition is…
cs.CV2026
Can One-Shot Test-Time Data Augmentation Help with Generalization?
Yunwei Bai, Yao Shu, Ying Kiat Tan +1
Data augmentation is crucial for model generalization, but existing methods are mostly centered on the training stage. Test-time augmentation, while underexplored, can be practical…
cs.CV2024
FSL-Rectifier: Rectify Outliers in Few-Shot Learning via Test-Time Augmentation
Yunwei Bai, Ying Kiat Tan, Shiming Chen +2
Few-shot learning (FSL) commonly requires a model to identify images (queries) that belong to classes unseen during training, based on a few labelled samples of the new classes (su…