Scaling Vision Transformers Without Training: Prune-and-Merge Token Compression
Read the original on arXiv AI →The paper introduces Prune-and-Merge ViT, a training‑free token compression framework for Vision Transformers that combines class‑attention pruning with similarity‑based merging to reduce computational cost while preserving semantic information. It evaluates robustness using two new metrics—Relative Accuracy Drop (RAD) and Prediction Flip Rate (PFR)—and shows that the method maintains or improves accuracy on pretrained ViT and DeiT models compared to existing token reduction techniques. The authors also argue that the hybrid approach does not induce hallucination‑like behavior and keeps predictions stable under common image transformations.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.