Uncertainty-Guided Inference-Time Depth Adaptation for Transformer-Based Visual Tracking

arXiv:2602.16160v2 Announce Type: replace Abstract: Transformer-based single-object trackers achieve state-of-the-art accuracy but rely on fixed-depth inference, executing the full encoder--decoder stack for every frame regardless of visual complexity, thereby incurring unnece...

🔗 Read more: https://arxiv.org/abs/2602.16160

#News #Software #Policy #Energy #Astronomy #Academic