1% VS 100%: Parameter-Efficient Low Rank Adapter for Dense Predictions

2023-01-01 · CVPR 2023 1 · Dongshuo Yin, Yiran Yang, Zhechao Wang, Hongfeng Yu, Kaiwen Wei, Xian Sun

Fine-tuning large-scale pre-trained vision models to downstream tasks is a standard technique for achieving state-of-the-art performance on computer vision benchmarks. However, fine-tuning the whole model with millions of parameters is inefficient as it requires storing a same-sized new model copy for each task. In this work, we propose LoRand, a method for fine-tuning large-scale vision models with a better trade-off between task performance and the number of trainable parameters. LoRand generates tiny adapter structures with low-rank synthesis while keeping the original backbone parameters fixed, resulting in high parameter sharing. To demonstrate LoRand's effectiveness, we implement extensive experiments on object detection, semantic segmentation, and instance segmentation tasks. By only training a small percentage (1% to 3%) of the pre-trained backbone parameters, LoRand achieves comparable performance to standard fine-tuning on COCO and ADE20K and outperforms fine-tuning in low-resource PASCAL VOC dataset.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Instance Segmentation object-detection Object Detection Segmentation Semantic Segmentation

Methods 이 논문이 사용한 방법론

Adapter 설명 없음

Parameter-Efficient Sparse Retrievers and Rerankers using Adapters

2023-03-23 · Vaishali Pal, Carlos Lassance, Hervé Déjean, Stéphane Clinchant

Parameter-Efficient transfer learning with Adapters have been studied in Natural Language Processing (NLP) as an alternative to full fine-tuning. Adapters are memory-efficient and scale well with downstream tasks by trai…

Domain Adaptation Information Retrieval Language Modelling Retrieval+1

Parameter-efficient is not sufficient: Exploring Parameter, Memory, and Time Efficient Adapter Tuning for Dense Predictions

2023-06-16 · Dongshuo Yin, Xueting Han, Bin Li, Hao Feng 외

Pre-training & fine-tuning is a prevalent paradigm in computer vision (CV). Recently, parameter-efficient transfer learning (PETL) methods have shown promising performance in adapting to downstream tasks with only a few …

Transfer Learning

Vision Transformer Adapter for Dense Predictions

2022-05-17 · Zhe Chen, Yuchen Duan, Wenhai Wang, Junjun He 외

This work investigates a simple yet powerful dense prediction task adapter for Vision Transformer (ViT). Unlike recently advanced variants that incorporate vision-specific inductive biases into their architectures, the p…

Instance Segmentation Object Detection Panoptic Segmentation Real-Time Object Detection+1

Signs Beat Floats: Low-Rank Double-Binary Adaptation for On-Device Fine-Tuning

2026-05-22 · Yoshihiko Fujisawa, Yuma Ichikawa, Yudai Fujimoto, Akira Sakai 외 arxiv

On-device adaptation of large language models commonly keeps a quantized base model frozen while training and deploying a small, task-specific LoRA adapter. In the unmerged adapter-mode setting, however, the adapter is m…

Sparsity-Aware Low-Rank Representation for Efficient Fine-Tuning of Large Language Models

2026-01-08 · Longteng Zhang, Sen Wu, Shuai Hou, Zhengyu Qing 외 arxiv

Adapting large pre-trained language models to downstream tasks often entails fine-tuning millions of parameters or deploying costly dense weight updates, which hinders their use in resource-constrained environments. Low-…

Model Compression