TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers

Le résumé fourni par la source

Vision Transformers (ViTs) achieve strong performance in image classification but incur high computational costs from processing all image tokens. To reduce inference costs in large ViTs without compromising accuracy, we propose Tiny-Drop, a training-free token dropping framework guided by a lightweight vision model. The guidance model estimates the importance of tokens while performing inference, thereby selectively discarding low-importance tokens for large ViT models. The framework operates plug-and-play, requires no architectural modifications, and is compatible with diverse ViT architectures. Evaluations on standard image classification benchmarks demonstrate that our framework reduces FLOPs by up to 80% for ViTs with minimal accuracy degradation, highlighting its generalization capability and practical utility for efficient ViT-based classification.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.