MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning

arXiv:2404.05621v1 Announce Type: new
Abstract: While excellent in transfer learning, Vision-Language models (VLMs) come with high computational costs due to their large number of parameters. To address this issue, removing parameters via model pruning is a viable solution. However, existing techniques for VLMs are task-specific, and thus require pruning the network from scratch for each new task of interest. In this work, we explore a new direction: Task-Agnostic Vision-Language Pruning (TA-VLP). Given a pretrained VLM, the goal is to find …

arxiv cs.cv language pruning type vision