3 papers
cs.LG2026
FOGO: Forgetting-aware Orthogonalization Optimizer
Toan Nguyen, Yang Liu, Trung Le +2
We argue that forgetting is not confined to continual learning but is a general optimization phenomenon: during standard training, dominant mini-batch gradients suppress rare but u…
cs.CV2025
Effective Dual-Region Augmentation for Reduced Reliance on Large Amounts of Labeled Data
Prasanna Reddy Pulakurthi, Majid Rabbani, Celso M. de Melo +2
This paper introduces a novel dual-region augmentation approach designed to reduce reliance on large-scale labeled datasets while improving model robustness and adaptability across…
cs.CV2025
Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation
Prasanna Reddy Pulakurthi, Majid Rabbani, Jamison Heard +3
This work investigates Source-Free Domain Adaptation (SFDA), where a model adapts to a target domain without access to source data. A new augmentation technique, Shuffle PatchMix (…