AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Searching for Network Width With Bilaterally Coupled Network

Xiu Qin Su, Shan You, Jiyang Xie, Fei Wang, Chen Qian, Changshui Zhang, Chang Xu

TPAMI 2022 · Architectures and efficiency › Neural architecture search · approach: One-shot and few-shot supernets · 12 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
add BCNet bilaterally coupled supernet (greedy search) (ablation)AutoSlim-style supernet · ImageNet, MobileNetV2 150MTop-1 accuracy: 69.52% -> 69.87%Improved
add BCNet bilaterally coupled supernet (greedy search) (ablation)AutoSlim-style supernet · ImageNet, ResNet50 2GTop-1 accuracy: 75.64% -> 76.30%Improved
add complementary training to BCNet (greedy search) (ablation)BCNet · ImageNet, MobileNetV2 150MTop-1 accuracy: 69.87% -> 69.91%Improved
add complementary training to BCNet (random-init evolutionary) (ablation)BCNet · ImageNet, ResNet50 2GTop-1 accuracy: 76.41% -> 76.56%Improved
add prior initial population sampling to evolutionary search (ablation)BCNet + complementary training · ImageNet, MobileNetV2 150MTop-1 accuracy: 70.04% -> 70.20%Improved
add base widths (BCNetV2 shrunk search space) (ablation)BCNet + complementary training + prior sampling · ImageNet, MobileNetV2 150MTop-1 accuracy: 70.20% -> 70.71%Improved
add base widths (BCNetV2 shrunk search space) (ablation)BCNet + complementary training + prior sampling · ImageNet, ResNet50 2GTop-1 accuracy: 76.90% -> 77.28%Improved
replace AutoSlim supernet with BCNet in supernet rankingAutoSlim · Channel-Bench-Macro, MobileNetKendall tau (%): 60.4 -> 65.2Improved
replace AutoSlim supernet with BCNet in supernet rankingAutoSlim · Channel-Bench-Macro, ResNetKendall tau (%): 61.2 -> 68.4Improved
use iterative updating instead of joint update in BCNetV2 (half memory) (ablation)BCNetV2 · ImageNet, MobileNetV2 150MTop-1 accuracy: 70.7% -> 70.7%No clear effect
replace uniform 0.5x ResNet50 backbone with BCNet-searched 2G backboneUniform ResNet50 · COCO RetinaNetdetection score: 34.3% -> 35.4%Improved
replace uniform ResNet50 backbone with BCNet-searched backboneUniform ResNet50 · COCO Faster R-CNNdetection score: 35.4% -> 36.3%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