Uncovering the Hidden Cost of Model Compression

arXiv:2308.14969v3 Announce Type: replace
Abstract: In an age dominated by resource-intensive foundation models, the ability to efficiently adapt to downstream tasks is crucial. Visual Prompting (VP), drawing inspiration from the prompting techniques employed in Large Language Models (LLMs), has emerged as a pivotal method for transfer learning in the realm of computer vision. As the importance of efficiency continues to rise, research into model compression has become indispensable in alleviating the computational burdens associated with training and deploying over-parameterized neural …

abstract adapt age arxiv compression computer computer vision cost cs.cv cs.lg foundation hidden inspiration language language models large language large language models llms pivotal prompting tasks transfer transfer learning type vision visual visual prompting