AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Model Stock: All we need is just a few fine-tuned models

Dong-Hwan Jang, Sangdoo Yun, Dongyoon Han

ECCV 2024 · Architectures and efficiency › Pruning and efficient tuning · approach: Adapter-based parameter-efficient tuning · 41 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
average more fine-tuned weights (approach the weight-space center) (ablation)CLIP ViT-B/32 fine-tuned on ImageNet · ImageNet / avg. shiftsaccuracy: ImageNet 79.72 -> 80.59; shifts 46.37 -> 48.85Improved
use two fine-tuned models plus the pre-trained anchor with geometric layer-wise interpolation instead of 48-model Model SoupCLIP ViT-B/32 · ImageNet (zero-shot init)top-1 accuracy: 79.76 (uniform soup) -> 79.89 at cost 48 -> 2No clear effect
Model Stock instead of Uniform Model Soup on distribution shiftsCLIP ViT-B/32 (zero-shot init) · avg. shiftsaccuracy: 52.08 -> 50.99Hurt
Model Stock* with LP init and strong augmentation versus vanilla fine-tuningCLIP ViT-B/32 · ImageNet (LP init)top-1 accuracy: 79.72 -> 81.19Improved
Model Stock instead of vanilla fine-tuningCLIP ViT-L/14 · avg. distribution shiftsaccuracy: 68.0 -> 73.5 (Model Stock* vs Vanilla FT*)Improved
increase number of merged models N from 2 to 4 at fixed training cost (ablation)Model Stock · ImageNet / avg. shifts (ViT-B/32)accuracy: IN 80.1 -> 80.4; shifts 48.8 -> 48.9Improved
vary merging period from 1000 or 5000 iterations to 1 epoch (ablation)Model Stock · ImageNet / avg. shifts (ViT-B/32)accuracy: avg shifts 48.7 / 48.5 / 48.8No clear effect
use geometric interpolation with pre-trained anchor (post-training) instead of uniform averaging (ablation)Model Stock · avg. shifts (ViT-B/32, N=2)accuracy: 47.8 -> 50.4Improved
use geometric interpolation instead of uniform averaging on ImageNet accuracy (ablation)Model Stock (post-training) · ImageNet (ViT-B/32, N=3,4)top-1 accuracy: +0.0 for N=3 and N=4No clear effect
random-perturbed weights nearer the weight center (ablation)CLIP ViT-B/32 · ImageNetaccuracy vs distanceImproved

Later papers that compared with this method

2 later accepted papers report ModelStock as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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