AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Neural Architecture Search for Lightweight Non-Local Networks

Yingwei Li, Xiaojie Jin, Jieru Mei, Xiaochen Lian, Linjie Yang, Cihang Xie, Qihang Yu, Yuyin Zhou, Song Bai, Alan L. Yuille

CVPR 2020 · Architectures and efficiency › Neural architecture search · approach: Latency-aware architecture search · 52 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
Add the proposed LightNL blocks to MobileNetV2 at the reported manual configurationMobileNetV2 · ImageNetTop-1 accuracy: 73.4% to 75.0%Improved
Add LightNL blocksMobileNetV2 backbone in Deeplabv3 · PASCAL VOC 2012mIoU: 70.6 to 72.9Improved
Replace the conventional non-local block with LightNL (ablation)MobileNetV2 · ImageNetTop-1 accuracy: 75.2% vs. 75.0%No clear effect
Use the full LightNL design instead of conventional non-local computation (ablation)MobileNetV2 · ImageNetFLOPs increase: +6.2G vs. +15MImproved
Search the placement and compactness of LightNL blocks with AutoNLMobileNetV2-family mobile architecture · ImageNet 2012 ValTop-1 accuracy: 76.3 to 77.7Improved
Use AutoNL-L rather than MobileNetV3-L (1.25x)MobileNetV3-L (1.25x) · ImageNet 2012 ValTop-1 accuracy: 76.6 to 77.7Improved
Use AutoNL-S rather than MobileNetV2MobileNetV2 · ImageNet 2012 ValTop-1 accuracy: 72.0 to 76.5Improved
Share and lighten feature transformations, remove the separate g transform, and use depthwise convolution for the residual transform (ablation)LightNL block · ImageNetTop-1 accuracy: 75.2, 75.1, 75.0, 75.0No clear effect
Use compact features to compute affinity matrices (ablation)LightNL block · ImageNetFLOPs: +119M, +93M, +66M, +38M, +15MImproved

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