AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Dropout Mixture Low-Rank Adaptation for Visual Parameters-Efficient Fine-Tuning

Zhengyi Fang, Yue Wang, Ran Yi, Lizhuang Ma

ECCV 2024 · Architectures and efficiency › Pruning and efficient tuning · approach: Adapter-based parameter-efficient tuning · 7 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 DMLoRA-LS instead of best prior PEFT methodViT-B/16 PEFT · VTAB-1K (19 tasks avg)accuracy: 76.1 -> 77.0Improved
use DMLoRA-LS instead of SSF on FGVCViT-B/16 PEFT · FGVC (5 datasets avg)accuracy: 90.7 -> 90.7No clear effect
gradually halve branches during training instead of keeping n branches (ablation)DMLoRA · VTAB-1K (avg)accuracy: 74.5 -> 76.6Improved
prune branches by random dropout instead of parameter averaging (ablation)DMLoRA · VTAB-1K (avg)accuracy: 74.8 -> 76.6Improved
use multiple up and down branches instead of sharing the up matrix (ablation)DMLoRA · VTAB-1K (avg)accuracy: 75.2 -> 76.6Improved
use multiple up and down branches instead of sharing the down matrix (ablation)DMLoRA · VTAB-1K (avg)accuracy: 75.5 -> 76.6Improved
learn the scale in a second stage with frozen LoRA matrices instead of jointly (ablation)DMLoRA · VTAB-1K (avg)accuracy: 75.4 -> 77.0Improved
use DMLoRA-LS vs prior methods on structured VTAB tasks sNORB-Azim and Caltech101ViT-B/16 PEFT · VTAB-1K per-taskaccuracy: 36.1 vs 38.6 (RepAdapter, sNORB-Azim); 90.7 vs 92.7 (NOAH, Caltech101)Mixed
add reparameterized LoRA branches at inference instead of Adapter/VPTDMLoRA-LS · ViT-B/16 inference latencyGPU latency (b=128): 1.37x -> 1x (vs VPT-Deep)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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