LION: Implicit Vision Prompt Tuning

arXiv:2303.09992v2 Announce Type: replace
Abstract: Despite recent competitive performance across a range of vision tasks, vision Transformers still have an issue of heavy computational costs. Recently, vision prompt learning has provided an economic solution to this problem without fine-tuning the whole large-scale models. However, the efficiency of existing models are still far from satisfactory due to insertion of extensive prompts blocks and trick prompt designs. In this paper, we propose an efficient vision model named impLicit vIsion prOmpt tuNing (LION), …

abstract arxiv computational costs cs.cv economic efficiency fine-tuning issue large-scale models performance prompt prompt learning prompt tuning scale solution tasks transformers type vision vision transformers