all AI news
FPT: Fine-grained Prompt Tuning for Parameter and Memory Efficient Fine Tuning in High-resolution Medical Image Classification
March 27, 2024, 4:47 a.m. | Yijin Huang, Pujin Cheng, Roger Tam, Xiaoying Tang
cs.CV updates on arXiv.org arxiv.org
Abstract: Parameter-efficient fine-tuning (PEFT) is proposed as a cost-effective way to transfer pre-trained models to downstream tasks, avoiding the high cost of updating entire large-scale pre-trained models (LPMs). In this work, we present Fine-grained Prompt Tuning (FPT), a novel PEFT method for medical image classification. FPT significantly reduces memory consumption compared to other PEFT methods, especially in high-resolution contexts. To achieve this, we first freeze the weights of the LPM and construct a learnable lightweight side …
abstract arxiv classification cost cs.cv fine-grained fine-tuning image medical memory novel peft pre-trained models prompt prompt tuning resolution scale tasks transfer type work
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead Data Engineer
@ WorkMoney | New York City, United States - Remote