paper-with-me

홈 › Papers

FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer

2022-12-06 · Shibo Jie, Zhi-Hong Deng

Recent work has explored the potential to adapt a pre-trained vision transformer (ViT) by updating only a few parameters so as to improve storage efficiency, called parameter-efficient transfer learning (PETL). Current PETL methods have shown that by tuning only 0.5% of the parameters, ViT can be adapted to downstream tasks with even better performance than full fine-tuning. In this paper, we aim to further promote the efficiency of PETL to meet the extreme storage constraint in real-world applications. To this end, we propose a tensorization-decomposition framework to store the weight increments, in which the weights of each ViT are tensorized into a single 3D tensor, and their increments are then decomposed into lightweight factors. In the fine-tuning process, only the factors need to be updated and stored, termed Factor-Tuning (FacT). On VTAB-1K benchmark, our method performs on par with NOAH, the state-of-the-art PETL method, while being 5x more parameter-efficient. We also present a tiny version that only uses 8K (0.01% of ViT's parameters) trainable parameters but outperforms full fine-tuning and many other PETL methods such as VPT and BitFit. In few-shot settings, FacT also beats all PETL baselines using the fewest parameters, demonstrating its strong capability in the low-data regime.

📄 PDF Abstract BibTeX arXiv:2212.03145

Code (1)

jieshibo/petl-vit 공식 구현 pytorch

Tasks

8kTransfer Learning

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

Who Needs Labels? Adapting Vision Foundation Models With the Metadata You Already Have

2026-06-03 · Elouan Gardès, Seung Eun Yi, Kartik Ahuja, Théo Moutakanni 외 arxiv

We propose a label-free approach to adapt powerful but generic vision foundation models to specialized scientific domains. Standard supervised fine-tuning is often ill-suited to these settings: labels are scarce, and tas…

Unsupervised Domain Adaptation

Black-Box Tuning of Vision-Language Models with Effective Gradient Approximation

2023-12-26 · Zixian Guo, Yuxiang Wei, Ming Liu, Zhilong Ji 외

Parameter-efficient fine-tuning (PEFT) methods have provided an effective way for adapting large vision-language models to specific tasks or scenarios. Typically, they learn a very small scale of parameters for pre-train…

parameter-efficient fine-tuning

Ravan: Multi-Head Low-Rank Adaptation for Federated Fine-Tuning

2025-06-05 · Arian Raje, Baris Askin, Divyansh Jhunjhunwala, Gauri Joshi

Large language models (LLMs) have not yet effectively leveraged the vast amounts of edge-device data, and federated learning (FL) offers a promising paradigm to collaboratively fine-tune LLMs without transferring private…

Federated Learning

Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach

2026-07-23 · Yuhua Wang, Xiaodong Li, Yihao Guo, Yuxiang Jia 외 arxiv

Federated prompt tuning (FPT) enables collaborative adaptation of vision--language models (VLMs) using lightweight prompts. Existing methods often address heterogeneity and privacy through a split-prompt design under loc…

LORA-CRAFT: Cross-layer Rank Adaptation via Frozen Tucker Decomposition of Pre-trained Attention Weights

2026-02-19 · Kasun Dewage, Marianna Pensky, Suranadi De Silva, Shankadeep Mondal arxiv

We introduce CRAFT (Cross-layer Rank Adaptation via Frozen Tucker), a parameter-efficient fine-tuning (PEFT) method that applies Tucker tensor decomposition to pre-trained attention weight matrices stacked across transfo…

parameter-efficient fine-tuning