paper-with-me

홈 › Papers

Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach

2024-03-28 · CVPR 2024 1 · Wei Dong, Xing Zhang, Bihui Chen, Dawei Yan, Zhijun Lin, Qingsen Yan, Peng Wang, Yang Yang

Parameter-efficient fine-tuning for pre-trained Vision Transformers aims to adeptly tailor a model to downstream tasks by learning a minimal set of new adaptation parameters while preserving the frozen majority of pre-trained parameters. Striking a balance between retaining the generalizable representation capacity of the pre-trained model and acquiring task-specific features poses a key challenge. Currently, there is a lack of focus on guiding this delicate trade-off. In this study, we approach the problem from the perspective of Singular Value Decomposition (SVD) of pre-trained parameter matrices, providing insights into the tuning dynamics of existing methods. Building upon this understanding, we propose a Residual-based Low-Rank Rescaling (RLRR) fine-tuning strategy. This strategy not only enhances flexibility in parameter tuning but also ensures that new parameters do not deviate excessively from the pre-trained model through a residual design. Extensive experiments demonstrate that our method achieves competitive performance across various downstream image classification tasks, all while maintaining comparable new parameters. We believe this work takes a step forward in offering a unified perspective for interpreting existing methods and serves as motivation for the development of new approaches that move closer to effectively considering the crucial trade-off mentioned above. Our code is available at \href{https://github.com/zstarN70/RLRR.git}{https://github.com/zstarN70/RLRR.git}.

📄 PDF Abstract BibTeX arXiv:2403.19067

Code (1)

zstarn70/rlrr 공식 구현 pytorch

Tasks

image-classificationImage Classificationparameter-efficient fine-tuning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Focus 설명 없음

Similar Papers 제목 키워드 기반

Effective Fine-Tuning of Vision Transformers with Low-Rank Adaptation for Privacy-Preserving Image Classification

2025-07-16 · Haiwei Lin, Shoko Imaizumi, Hitoshi Kiya arxiv

We propose a low-rank adaptation method for training privacy-preserving vision transformer (ViT) models that efficiently freezes pre-trained ViT model weights. In the proposed method, trainable rank decomposition matrice…

Image Classification

LoCO: Low-rank Compositional Rotation Fine-tuning

2026-05-15 · An Nguyen, Jaesik Choi, Anh Tong arxiv

Parameter-efficient fine-tuning (PEFT) has emerged as an critical technique for adapting large-scale foundation models across natural language processing and computer vision. While existing methods such as low-rank adapt…

parameter-efficient fine-tuning

Deep Reinforcement Learning for Mention-Ranking Coreference Models

2016-09-27 · EMNLP 2016 11 · Kevin Clark, Christopher D. Manning

Coreference resolution systems are typically trained with heuristic loss functions that require careful tuning. In this paper we instead apply reinforcement learning to directly optimize a neural mention-ranking model fo…

coreference-resolutionCoreference ResolutionDeep Reinforcement Learningreinforcement-learning+2

LangVision-LoRA-NAS: Neural Architecture Search for Variable LoRA Rank in Vision Language Models

2025-08-17 · Krishna Teja Chitty-Venkata, Murali Emani, Venkatram Vishwanath arxiv

Vision Language Models (VLMs) integrate visual and text modalities to enable multimodal understanding and generation. These models typically combine a Vision Transformer (ViT) as an image encoder and a Large Language Mod…

Neural Architecture SearchComputational EfficiencyText Generation

RandLoRA: Full-rank parameter-efficient fine-tuning of large models

2025-02-03 · Paul Albert, Frederic Z. Zhang, Hemanth Saratchandran, Cristian Rodriguez-Opazo 외

Low-Rank Adaptation (LoRA) and its variants have shown impressive results in reducing the number of trainable parameters and memory requirements of large transformer networks while maintaining fine-tuning performance. Th…

parameter-efficient fine-tuning