AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

PWLU: Learning Specialized Activation Functions With the Piecewise Linear Unit

Zezhou Zhu, Yucong Zhou, Yuan Dong, Zhao Zhong

TPAMI 2023 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 18 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 statistic-based boundary realignment instead of fixed init (x=10) (ablation)channel-wise PWLU, ResNet-18 · ImageNet-1k valtop-1 accuracy (%): 72.19 -> 72.57Improved
add statistic-based boundary realignment instead of fixed init (x=10) (ablation)channel-wise PWLU, MobileNet-V3 · ImageNet-1k valtop-1 accuracy (%): 68.20 -> 69.65Improved
add statistic-based realignment instead of fixed init (x=10) (ablation)layer-wise PWLU, ResNet-18 · ImageNet-1k valtop-1 accuracy (%): 71.84 -> 72.22Improved
add statistic-based realignment instead of fixed init (x=3) (ablation)layer-wise PWLU, MobileNet-V3 · ImageNet-1k valtop-1 accuracy (%): 68.54 -> 69.30Improved
use channel-wise instead of layer-wise PWLU (ablation)PWLU stat-realign, ResNet-18 · ImageNet-1k valtop-1 accuracy (%): 72.22 -> 72.57Improved
use 8 intervals instead of 4 (ablation)channel-wise PWLU, MobileNet-V3 · ImageNet-1k valtop-1 accuracy (%): 68.70 -> 69.55Improved
use 16 intervals instead of 4 (ablation)channel-wise PWLU, ResNet-18 · ImageNet-1k valtop-1 accuracy (%): 72.24 -> 72.57Improved
use 20 intervals instead of 16 (ablation)channel-wise PWLU, MobileNet-V3 · ImageNet-1k valtop-1 accuracy (%): 69.65 -> 69.37Hurt
use 20 intervals instead of 16 (ablation)channel-wise PWLU, EfficientNet-B0 · ImageNet-1k valtop-1 accuracy (%): 78.22 -> 77.86Hurt
replace ReLU with PWLUMobileNet-V3 · ImageNet-1k valtop-1 accuracy (%): 67.74 -> 69.65Improved
replace ReLU with PWLUResNet-18 · ImageNet-1k valtop-1 accuracy (%): 71.34 -> 72.57Improved
replace Swish with PWLUMask R-CNN ResNet-50-FPN · COCO val2017box AP: 40.05 -> 40.48Improved

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