Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers
Overview
This research introduces a token selection strategy for Visual Geometry Transformers (ViT) to address their quadratic computational cost. The proposed two-stage framework first selects key frames based on diversity and then performs layer-aware sparsification within those frames guided by attention entropy. Experiments show the method accelerates inference by over 85% for scenes with 500 images while maintaining or improving baseline performance, offering a superior speed-accuracy trade-off.
Generated from attributed reports · Updated 1 days ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
No current evidence-backed claims. Missing information remains not reported.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalGood Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers
This research introduces a token selection strategy for Visual Geometry Transformers (ViT) to address their quadratic computational cost. The proposed two-stage framework first selects key frames based on diversity and then performs layer-aware sparsification within those frames guided by attention entropy. Experiments show the method accelerates inference by over 85% for scenes with 500 images while maintaining or improving baseline performance, offering a superior speed-accuracy trade-off.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).