AI Paper Atlas

Research map / Architectures and efficiency / CNN design

SRM: A Style-Based Recalibration Module for Convolutional Neural Networks

HyunJae Lee, Hyo-Eun Kim, Hyeonseob Nam

ICCV 2019 · Architectures and efficiency › CNN design · approach: Filter design and trained-filter analysis · 382 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 StdPool to AvgPool in style pooling (ablation)SRM · ImageNet-1K val (ResNet-50)top-1 accuracy (%): 76.58 -> 77.13Improved
use StdPool + AvgPool instead of AvgPool + MaxPool (ablation)SRM · ImageNet-1K val (ResNet-50)top-1 accuracy (%): 76.35 -> 77.13Improved
add MaxPool as the only pooling (ablation)SRM · ImageNet-1K val (ResNet-50)top-1 accuracy (%): 75.89 -> 75.87No clear effect
use channel-wise FC (CFC) instead of MLP for style integration (ablation)SRM · ImageNet-1K val (ResNet-50)top-1 accuracy (%): 76.75 -> 76.91Improved
add batch normalization after CFC (ablation)SRM · ImageNet-1K val (ResNet-50)top-1 accuracy (%): 76.91 -> 77.13Improved
add batch normalization after MLP (ablation)SRM · ImageNet-1K val (ResNet-50)top-1 accuracy (%): 76.75 -> 76.68Hurt
add SRM to ResNet-50 instead of SE (ablation)ResNet-50 · ImageNet-1K valtop-1 accuracy (%): 76.80 -> 77.13Improved
add SRM to ResNet-101ResNet-101 · ImageNet-1K valtop-1 accuracy (%): 77.40 -> 78.47Improved
add GE to ResNet-101ResNet-101 · ImageNet-1K valtop-1 accuracy (%): 77.40 -> 77.36No clear effect
add SRM to ResNet-56ResNet-56 · CIFAR-100top-1 accuracy (%): 74.76 -> 76.93Improved
add SRM to ResNet-50 trained on Stylized-ImageNetResNet-50 · Stylized-ImageNettop-1 accuracy (%): 53.93 -> 60.69Improved
add SRM to ResNet-18 on Office-HomeResNet-18 · Office-Homeaccuracy (%): 55.47 -> 59.47Improved

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