AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Adaptive Parametric Activation

Konstantinos P Alexandridis, Jiankang Deng, Anh Nguyen, Shan Luo

ECCV 2024 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 9 citations (OpenAlex)

This paper tried a common change: Add dropout

add dropout to APA attention · ImageNet-LT · average top-1 accuracy: 57.0 -> 57.3 Improved

What 795 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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
replace Sigmoid in channel attention with APA (ablation)SE-ResNet50 · ImageNet-LTaverage top-1 accuracy: 56.0 -> 57.0Improved
use APA instead of Gumbel with learnable temperature (ablation)SE-ResNet50 · ImageNet-LTaverage top-1 accuracy: 56.7 -> 57.0Improved
add learnable temperature to Sigmoid (ablation)SE-ResNet50 · ImageNet-LTMany-shot accuracy: Few 37.1 -> 40.3; Many 66.2 -> 65.9Mixed
add channel attention (SE) to plain ResNet50 (ablation)ResNet50 · ImageNet-LTaverage top-1 accuracy: 55.0 -> 56.0Improved
add dropout to APA attention (ablation)SE + APA ResNet50 · ImageNet-LTaverage top-1 accuracy: 57.0 -> 57.3Improved
add LayerNorm to APA attention (ablation)SE + APA + Dropout ResNet50 · ImageNet-LTaverage top-1 accuracy: 57.3 -> 57.4No clear effect
replace ReLU with AGLU in intermediate layers (ablation)APA* ResNet50 · ImageNet-LTaverage top-1 accuracy: 57.4 -> 57.9Improved
use PReLU or ELU instead of ReLU as intermediate activation (ablation)APA* ResNet50 · ImageNet-LTaverage top-1 accuracy: 57.4 -> 54.8 (PReLU), 52.6 (ELU)Hurt
use APA* with deeper ResNet-101 (ablation)SE-ResNet101 · ImageNet-LTaverage top-1 accuracy: 56.7 -> 58.8Improved
add APA* to classifier learning methods such as cRT and BSCE (ablation)ImageNet-LT classifier learning · ImageNet-LTaverage top-1 accuracy: CE 51.7 -> 52.9; BSCE 56.0 -> 57.0Improved
add APA to Spatial attention (ablation)Spatial attention ResNet50 · ImageNet-LTaverage top-1 accuracy: 54.8 -> 55.2Improved
add APA*+AGLU to SE-ResNet50 on balanced ImageNet1KSE-ResNet50 · ImageNet1Ktop-1 accuracy: 77.5 -> 78.7Improved

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