AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search

Bichen Wu, Xiaoliang Dai, Peizhao Zhang, Yanghan Wang, Fei Sun, Yiming Wu, Yuandong Tian, Peter Vajda, Yangqing Jia, Kurt Keutzer

CVPR 2019 · Architectures and efficiency › Neural architecture search · approach: Latency-aware architecture search · 1,331 citations (OpenAlex)

Check 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 layer-wise differentiable search with target-device latency optimization instead of manual designFBNet-A · ImageNet validation on Samsung Galaxy S8CPU latency: 21.7 ms -> 19.8 msImproved
Use layer-wise differentiable search with target-device latency optimization instead of manual designFBNet-A · ImageNet validationTop-1 accuracy (%): 72.0 -> 73.0Improved
Use layer-wise differentiable search with target-device latency optimization instead of RL-based searchFBNet-B · ImageNet validationTop-1 accuracy (%): 74.0 -> 74.1Improved
Use layer-wise differentiable search with target-device latency optimization instead of RL-based searchFBNet-B · ImageNet validation on Samsung Galaxy S8CPU latency: 23.7 ms -> 23.1 msImproved
Search a model for the target input resolution and channel scaling rather than reuse MobileNetV2 structureFBNet family · ImageNet with varied input resolution and channel scalingTop-1 accuracy (%): 1.5% to 6.4%Improved
Search a model for the target device rather than reuse a Samsung S8-optimized modelFBNet-iPhoneX · ImageNet on iPhone XLatency: 27.53 ms -> 19.84 msImproved
Use a reduced-resolution, searched architectureFBNet-96-0.35-1 · ImageNet (96, 0.35)CPU latency: 3.8 ms -> 2.9 msImproved

Later papers that compared with this method

1 later accepted paper reports FBNet-96-0.35-1 as a baseline in their results tables; 1 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