AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Auto-DAS: Automated Proxy Discovery for Training-free Distillation-aware Architecture Search

Haosen Sun, Lujun Li, Peijie Dong, Zimian Wei, Shitong Shao

ECCV 2024 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS · 6 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
evolve proxies from scratch over instinct and interaction statistics instead of manual DisWOT proxyAuto-DAS · NAS-Bench-101-KDSpearman correlation (%): 52.45 -> 85.95Improved
use DisWOT handcrafted proxy on ViT search spaceDisWOT · ViT-Bench PiT CIFAR-100Kendall correlation (%): -19.05Hurt
use Auto-DAS searched student instead of DisWOT student under equal constraintsNDS-ResNet CIFAR-100 · NDS-ResNet CIFAR-100accuracy (%): 74.23 -> 74.66 (1M params)Improved
use Auto-DAS searched students on ImageNet instead of DisWOTResNet18/ResNet50 · ImageNet-1kTop-1 accuracy (%): 72.08 -> 72.58 (ResNet18); 78.62 -> 79.25 (ResNet50)Improved
combine instinct and interaction proxy inputs and operations (ablation)Auto-DAS proxy · PiT CIFAR-100 rankingSpearman correlation (%): 83.25 -> 90.32 (instinct-only vs full)Improved
use interaction proxy instead of instinct proxy only (ablation)Auto-DAS proxy · ResNet / NB-101 rankingSpearman correlation (%): ResNet 80.52 -> 92.82; NB-101 75.86 -> 50.88Mixed
use gradient-free Auto-DAS (ablation)Auto-DAS · PiT CIFAR-100distilled accuracy (%) / search cost: 77.88 -> 77.72; 1.28 h -> 0.82hNo clear effect
use adaptive-elite selection in the evolution (ablation)Auto-DAS proxy search · ResNet proxy search curvesearch resultImproved
apply Auto-DAS searched student under other KD methods (FitNets, AT, SP, RKD, CRD)1M-parameter students · NDS-ResNet CIFAR-100accuracy (%): 74.85 -> 75.28 (FitNets); 75.25 -> 75.86 (CRD)Improved

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