Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Zixuan, Wei, Yongxian, Shen, Li, Yuan, Chun, Tao, Dacheng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915045860966400
author Hu, Zixuan
Wei, Yongxian
Shen, Li
Yuan, Chun
Tao, Dacheng
author_facet Hu, Zixuan
Wei, Yongxian
Shen, Li
Yuan, Chun
Tao, Dacheng
contents Large Language Models (LLMs) such as ChatGPT demonstrate strong few-shot adaptability without requiring fine-tuning, positioning them ideal for data-limited and real-time applications. However, this adaptability has not yet been replicated in current Visual Foundation Models (VFMs), which require explicit fine-tuning with sufficient tuning data. Besides, the pretraining-finetuning paradigm has led to the surge of numerous task-specific modular components, such as Low-Rank Adaptation (LoRA). For the first time, we explore the potential of reusing diverse pre-tuned LoRAs without accessing their original training data, to achieve tuning-free few-shot adaptation in VFMs. Our framework, LoRA Recycle, distills a meta-LoRA from diverse pre-tuned LoRAs with a meta-learning objective, using surrogate data generated inversely from pre-tuned LoRAs themselves. The VFM, once equipped with the meta-LoRA, is empowered to solve new few-shot tasks in a single forward pass, akin to the in-context learning of LLMs. Additionally, we incorporate a double-efficient mechanism tailored to our framework, significantly accelerating the meta-training process while maintaining or even improving performance. Extensive experiments across various few-shot classification benchmarks across both in- and cross-domain scenarios demonstrate the superiority of our framework.
format Preprint
id arxiv_https___arxiv_org_abs_2412_02220
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs
Hu, Zixuan
Wei, Yongxian
Shen, Li
Yuan, Chun
Tao, Dacheng
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Large Language Models (LLMs) such as ChatGPT demonstrate strong few-shot adaptability without requiring fine-tuning, positioning them ideal for data-limited and real-time applications. However, this adaptability has not yet been replicated in current Visual Foundation Models (VFMs), which require explicit fine-tuning with sufficient tuning data. Besides, the pretraining-finetuning paradigm has led to the surge of numerous task-specific modular components, such as Low-Rank Adaptation (LoRA). For the first time, we explore the potential of reusing diverse pre-tuned LoRAs without accessing their original training data, to achieve tuning-free few-shot adaptation in VFMs. Our framework, LoRA Recycle, distills a meta-LoRA from diverse pre-tuned LoRAs with a meta-learning objective, using surrogate data generated inversely from pre-tuned LoRAs themselves. The VFM, once equipped with the meta-LoRA, is empowered to solve new few-shot tasks in a single forward pass, akin to the in-context learning of LLMs. Additionally, we incorporate a double-efficient mechanism tailored to our framework, significantly accelerating the meta-training process while maintaining or even improving performance. Extensive experiments across various few-shot classification benchmarks across both in- and cross-domain scenarios demonstrate the superiority of our framework.
title Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2412.02220