2 papers
cs.CV2025
Beyond Softmax: Dual-Branch Sigmoid Architecture for Accurate Class Activation Maps
Yoojin Oh, Junhyug Noh
Class Activation Mapping (CAM) and its extensions have become indispensable tools for visualizing the evidence behind deep network predictions. However, by relying on a final softm…
cs.CV2025
SteeringTTA: Guiding Diffusion Trajectories for Robust Test-Time-Adaptation
Jihyun Yu, Yoojin Oh, Wonho Bae +2
Test-time adaptation (TTA) aims to correct performance degradation of deep models under distribution shifts by updating models or inputs using unlabeled test data. Input-only diffu…