AI Paper Atlas

Research map / Architectures and efficiency / CNN design

WeightNet: Revisiting the Design Space of Weight Networks

Ningning Ma, Xiangyu Zhang, Jiawei Huang, Jian Sun

ECCV 2020 · Architectures and efficiency › CNN design · approach: Efficient CNN scaling and dynamic inference · 108 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 WeightNet (1x)ShuffleNetV2 0.5x · ImageNet valTop-1 error: 39.7 -> 36.7Improved
add WeightNet (1x)ShuffleNetV2 1x · ImageNet valTop-1 error: 30.9 -> 28.8Improved
raise lambda from 1 to 8 (ablation)WeightNet on ShuffleNetV2 0.5x · ImageNet valTop-1 error: 36.7 -> 34.0Improved
raise lambda from 4 to 8 (ablation)WeightNet on ShuffleNetV2 2x · ImageNet valTop-1 error: 23.5 -> 24.0Hurt
raise G from 1 to 4 (ablation)WeightNet on ShuffleNetV2 0.5x · ImageNet valTop-1 error: 37.18 -> 36.37Improved
apply WeightNet to stages 3 and 4 only instead of all stages (ablation)WeightNet on ShuffleNetV2 0.5x · ImageNet valTop-1 error: 35.47 -> 35.30Improved
add WeightNet to stage 4 only instead of stage 2 only (ablation)WeightNet on ShuffleNetV2 0.5x · ImageNet valTop-1 error: 39.13 -> 36.43Improved
use layer-wise GAP instead of stage-wise GAP (ablation)WeightNet (2x) on ShuffleNetV2 0.5x · ImageNet valTop-1 error: 37.01 -> 35.04Improved
replace SE with WeightNet (2x)ShuffleNetV2 1.5x · ImageNet valTop-1 error: 26.4 -> 25.2Improved
replace CondConv (4x) with WeightNet (2x)ShuffleNetV2 1.5x · ImageNet valTop-1 error: 26.1 -> 25.2Improved
add WeightNet (1x) instead of SEResNet50 · ImageNet valTop-1 error: 22.8 -> 22.5Improved
add WeightNet (4x) as backbone moduleRetinaNet ShuffleNetV2 0.5x · COCO minivalmAP: 22.5 -> 27.1Improved

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