Training-free token reduction accelerates vision transformers by removing redundant tokens across layers, recovering most of the original accuracy at a fraction of the compute. These methods, however, are designed and evaluated primarily on clean data, and under real-world distribution shift their accuracy gap to the u...
Quantizer-Aligned Recalibration (QuAR), a single-pass TTA method tailored to quantized ViTs that neither backpropagates nor updates any model parameters is proposed, which achieves the highest mean accuracy among state-of-the-art backpropagates nor updates any model parameters.
Hyeong-Tae Cha, Young D. Kwon, Sung-Ju Lee· 0 citations
A simple branch-regenerate-distill algorithm, Trajectory-Intervention Self-Distillation (TISD), which forces a teacher-selected branch action, returns suffix generation to the student, and distills the full trajectory under the privileged-context-conditioned teacher, support teacher-guided branching as a way to expose...
Taeckyung Lee, Rinat Amankos, Jeonghye Kim et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.