AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

InstaNAS: Instance-Aware Neural Architecture Search

An-Chieh Cheng, Chieh Hubert Lin, Da-Cheng Juan, Wei Wei, Min Sun

AAAI 2020 · Architectures and efficiency › Neural architecture search · approach: Efficient NAS search strategies · 46 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 instance-aware architecture selection rather than one fixed MobileNetV2 architectureInstaNAS · CIFAR-10latency: 48.9% latency reductionImproved
Select architectures per instance and choose the C10-A trade-offInstaNAS · CIFAR-10accuracy: improves accuracy by 1.26%Improved
Use instance-aware architecture selection rather than one fixed MobileNetV2 architectureInstaNAS · CIFAR-100latency: 40.2% latency reductionImproved
Use instance-aware architecture selection rather than one fixed MobileNetV2 architectureInstaNAS · TinyImageNetlatency: 35.2% latency reductionImproved
Use instance-aware architecture selection rather than one fixed MobileNetV2 architectureInstaNAS · ImageNetlatency: 14.5%Improved
Allow a moderate accuracy drop to select faster instance-specific architecturesInstaNAS · ImageNetlatency: 26.5% average latency reduction; $\simeq$ 0.7%Improved
Add random shuffling of selected policies during meta-graph fine-tuningInstaNAS · Search stabilitysearch successImproved

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