Suwoong Lee

Tailored ViT Slimming: Budget-Aware Multi-Dimensional Sparsity Regularization for Vision Transformers Pruning (Student Abstract)

We propose Tailored ViT Slimming (TVS), a budget-aware multi-dimensional pruning framework for Vision Transformers. TVS injects learnable masks into MHSA and MLP modules and applies adaptive non-convex sparsity regularization to achieve maximal utilization of parameters under strict module-wise budg