AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

AMD: Automatic Multi-step Distillation of Large-scale Vision Models

Cheng Han, Qifan Wang, Sohail A Dianat, Majid Rabbani, Raghuveer Rao, Yi Fang, Qiang Guan, Lifu Huang, Dongfang Liu

ECCV 2024 · Label-efficient and robust learning › Knowledge distillation · approach: Few-shot and metric distillation · 19 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 AMD multi-step distillation instead of MMD (manual search over teacher-assistants)AMD · CIFAR-100 (ViT-Base 10% student)GPU hours: 20x -> 2.2xImproved
AMD versus manual multi-step distillation in accuracyAMD · CIFAR-100 (ViT-Tiny 10% student)top-1 accuracy: 73.12 -> 73.10No clear effect
add feature-mimicking loss L_feat (ablation)AMD · CIFAR-100 (ViT-Base 10% student)top-1 accuracy: 75.24 -> 80.19Improved
add logit loss L_logit (ablation)AMD · CIFAR-100 (ViT-Base 10% student)top-1 accuracy: 78.01 -> 80.19Improved
add cross-entropy loss L_ce (ablation)AMD · CIFAR-100 (ViT-Base 10% student)top-1 accuracy: 78.32 -> 80.19Improved
add DKD loss on top of AMD objective (ablation)AMD · CIFAR-100 (ViT-Base 10% student)top-1 accuracy: 80.19 -> 80.22No clear effect
add one teacher-assistant versus none (ablation)AMD · CIFAR-100 (ViT-Base 10% student)top-1 accuracy: 79.77 -> 80.19Improved
use more than one teacher-assistant (ablation)AMD · CIFAR-100 (ViT-Base 10% student)top-1 accuracy: 80.19 -> 80.24No clear effect
increase candidate scales m from 1 to 9 (ablation)AMD · CIFAR-100 (ViT-Base 10% student)top-1 accuracy: 78.39 -> 80.19Improved
increase candidate scales m from 9 to 15 (ablation)AMD · CIFAR-100 (ViT-Base 10% student)top-1 accuracy: 80.19 -> 80.22No clear effect
use lambda-NPSD including student term instead of plain NPSD (ablation)AMD · CIFAR-100 (ViT-Base 10% student)top-1 accuracy: 80.19 -> 80.14No clear effect
use AMD instead of ADKD at 5% student scaleAMD · CIFAR-100 (ViT-Base 5% student)top-1 accuracy: 68.44 -> 75.88Improved

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