2 papers
cs.CV2026
Video Patch Pruning: Efficient Video Instance Segmentation via Early Token Reduction
Patrick Glandorf, Thomas Norrenbrock, Bodo Rosenhahn
Vision Transformers (ViTs) have demonstrated state-ofthe-art performance in several benchmarks, yet their high computational costs hinders their practical deployment. Patch Pruning…
cs.CV2025
Pruning by Block Benefit: Exploring the Properties of Vision Transformer Blocks during Domain Adaptation
Patrick Glandorf, Bodo Rosenhahn
Vision Transformer have set new benchmarks in several tasks, but these models come with the lack of high computational costs which makes them impractical for resource limited hardw…