paper-with-me

Papers

Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation

2024-03-18 · Wangbo Zhao, Jiasheng Tang, Yizeng Han, Yibing Song, Kai Wang, Gao Huang, Fan Wang, Yang You

Existing parameter-efficient fine-tuning (PEFT) methods have achieved significant success on vision transformers (ViTs) adaptation by improving parameter efficiency. However, the exploration of enhancing inference efficiency during adaptation remains underexplored. This limits the broader application of pre-trained ViT models, especially when the model is computationally extensive. In this paper, we propose Dynamic Tuning (DyT), a novel approach to improve both parameter and inference efficiency for ViT adaptation. Specifically, besides using the lightweight adapter modules, we propose a token dispatcher to distinguish informative tokens from less important ones, allowing the latter to dynamically skip the original block, thereby reducing the redundant computation during inference. Additionally, we explore multiple design variants to find the best practice of DyT. Finally, inspired by the mixture-of-experts (MoE) mechanism, we introduce an enhanced adapter to further boost the adaptation performance. We validate DyT across various tasks, including image/video recognition and semantic segmentation. For instance, DyT achieves superior performance compared to existing PEFT methods while evoking only 71% of their FLOPs on the VTAB-1K benchmark.

📄 PDF Abstract BibTeX arXiv:2403.11808

Code (1)

nus-hpc-ai-lab/dynamic-tuning 공식 구현 pytorch

Tasks

Mixture-of-Expertsparameter-efficient fine-tuningSemantic SegmentationVideo Recognition

Methods 이 논문이 사용한 방법론

Adapter 설명 없음

Similar Papers 제목 키워드 기반

C-LoRA: Continual Low-Rank Adaptation for Pre-trained Models

2025-02-25 · Xin Zhang, Liang Bai, Xian Yang, Jiye Liang

Low-Rank Adaptation (LoRA) is an efficient fine-tuning method that has been extensively applied in areas such as natural language processing and computer vision. Existing LoRA fine-tuning approaches excel in static envir…

Continual Learning

DLP-LoRA: Efficient Task-Specific LoRA Fusion with a Dynamic, Lightweight Plugin for Large Language Models

2024-10-02 · Yuxuan Zhang, Ruizhe Li

Recent advancements in Large Language Models (LLMs) have achieved robust performance across diverse tasks, but fine-tuning these models for specific domains remains resource-intensive. Parameter-Efficient Fine-Tuning (PE…

Multiple-choiceparameter-efficient fine-tuningQuestion AnsweringSentence

Hallucinations and Truth: A Comprehensive Accuracy Evaluation of RAG, LoRA and DoRA

2025-02-14 · Mohammad Baqar, Rajat Khanda

Recent advancements in Generative AI have significantly improved the efficiency and adaptability of natural language processing (NLP) systems, particularly through Retrieval-Augmented Generation (RAG), Low-Rank Adaptatio…

Domain Adaptationparameter-efficient fine-tuningRAGRetrieval-augmented Generation

Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model

2024-12-24 · Yushu Li, Yongyi Su, Adam Goodge, Kui Jia 외

Vision-language models (VLMs) have revolutionized machine learning by leveraging large pre-trained models to tackle various downstream tasks. Despite improvements in label, training, and data efficiency, many state-of-th…

Language ModelingLanguage ModellingOut-of-Distribution Generalization

Efficient Self-Supervised Adaptation for Medical Image Analysis

2025-03-24 · Moein Sorkhei, Emir Konuk, Jingyu Guo, Christos Matsoukas 외

Self-supervised adaptation (SSA) improves foundation model transfer to medical domains but is computationally prohibitive. Although parameter efficient fine-tuning methods such as LoRA have been explored for supervised a…

GPUMedical Image Analysisparameter-efficient fine-tuning