Hai-Feng Huo

SAGE: Saliency-Annealed Gated Encoder for Universal Vision Recognition

When adapting self-supervised Vision Transformers (ViTs) to dense prediction, existing methods often treat the ViT as a passive feature extractor and may underuse the rich priors encoded in its representations, including saliency, global context, and high-frequency details. We propose SAGE (Saliency-Annealed Gated Enco...