AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark

Yi Xin, Jianjiang Yang, Siqi Luo, Yuntao Du, Qi Qin, Haoxing Chen, Kangrui Cen, Yangfan He, Bin Fu, Yuewen Cao, Junjun He, Xiaokang Yang and 3 more

IJCV 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Efficient ViT adaptation · 188 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Adapter instead of full fine-tuningViT-B/16 · VTAB-1kmean accuracy: 65.57 -> 71.44Improved
use HST instead of full fine-tuningViT-B/16 · VTAB-1kmean accuracy: 65.57 -> 75.99Improved
use BitFit instead of full fine-tuningViT-B/16 · VTAB-1kmean accuracy: 65.57 -> 62.05Hurt
use VPT-Shallow instead of full fine-tuningViT-B/16 · VTAB-1kmean accuracy: 65.57 -> 64.85Hurt
use VPT-Deep instead of VPT-ShallowVPT · VTAB-1kmean accuracy: 64.85 -> 69.43Improved
use DTL for best performance-parameter trade-offViT-B/16 · VTAB-1kPPT: 0.75Improved
fine-tune with AdaptFormer instead of fullVideoMAE ViT-B · SSv2top-1 accuracy (%): 53.97 % -> 59.02 %Improved
freeze backbone instead of full fine-tuningVideoMAE ViT-B · HMDB51top-1 accuracy (%): 46.41 % -> 49.84 %Improved
use LoRA instead of full fine-tuningVideo Swin-B · SSv2top-1 accuracy (%): 50.99 % -> 38.34 %Hurt
use BAPAT instead of full fine-tuningVideo Swin-B · SSv2top-1 accuracy (%): 50.99 % -> 53.36 %Improved
use Prefix-tuning instead of AdaptFormerVideo Swin-B · HMDB51top-1 accuracy (%): 68.66 % -> 56.13 %Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy