AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Thanks for Nothing: Predicting Zero-Valued Activations with Lightweight Convolutional Neural Networks

Gil Shomron, Ron Banner, Moran Shkolnik, Uri Weiser

ECCV 2020 · Architectures and efficiency › CNN design · approach: Compact CNN architectures · 24 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
fine-tune the model after deploying ZAP (ablation)ZAP · CIFAR-100 AlexNetMAC reduction at about 1% top-1 drop: 32.4% MAC reduction with 0.7% degradation -> 40.3% with 0.8% degradationImproved
fine-tune the model after ZAP (ablation)ZAP · ILSVRC-2012 AlexNet (vs Shomron)top-1 accuracy degradation: 1.28 -> 0.78Improved
fine-tune the model after ZAP (ablation)ZAP · ILSVRC-2012 ResNet-18 (vs Shomron)top-1 accuracy degradation: 2.96 -> 1.86Improved
fine-tune the model after ZAP (ablation)ZAP · ILSVRC-2012 VGG-16 (vs Shomron)top-1 accuracy degradation: 1.71 -> 0.31Improved
use masks with larger computed ratio alpha (mask A vs D) (ablation)ZAP · CIFAR-100 AlexNettop-1 accuracy degradationMixed
raise the prediction threshold (ablation)ZAP · CIFAR-100 AlexNetmisprediction of non-zero activationsHurt
replace Figurnov et al. interpolation with ZAPZAP · ILSVRC-2012 AlexNettop-5 accuracy degradation: 8.50 -> 3.04Improved
replace Figurnov et al. with ZAPZAP · ILSVRC-2012 VGG-16top-5 accuracy degradation: 15.6 -> 7.02Improved
replace Shomron and Weiser with ZAPZAP · ILSVRC-2012 ResNet-18top-1 accuracy degradation: 11.0 -> 2.96Improved
replace Kim et al. with ZAPZAP · ILSVRC-2012 VGG-16top-5 accuracy degradation: 0.26 -> 0.33No clear effect
replace Dong et al. with ZAPZAP · ILSVRC-2012 ResNet-18top-5 accuracy degradation fine-tuned: 2.3 -> 4.66Hurt

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