AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Quantification and Analysis of Layer-wise and Pixel-wise Information Discarding

Haotian Ma, Hao Zhang, Fan Zhou, Yinqing Zhang, Quanshi Zhang

ICML 2022 · Architectures and efficiency › RNNs and normalization · approach: Representation geometry and collapse

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
Use CID rather than CAM or Grad-CAM for localization mapsResNet-50 on CUB200-2011 · CUB200-2011 weakly-supervised localizationlocalization accuracy: CAM 0.367; Grad-CAM 0.355; CID 0.493Improved
Use CID rather than Grad-CAM or LRP for localization mapsVGG-16 on CUB200-2011 · CUB200-2011 weakly-supervised localizationlocalization accuracy: Grad-CAM 0.507; LRP 0.489; CID 0.578Improved
Compress VGG-16 to 38.0% parameters (ablation)VGG-16 on CUB200-2011 · CUB200-2011 VGG-16 compressionadversarial robustness ||ε||₂: ΔCID -0.003; adversarial robustness 0.00281Mixed
Compress VGG-16 to 12.8% parameters (ablation)VGG-16 on CUB200-2011 · CUB200-2011 VGG-16 compressionadversarial robustness ||ε||₂: ΔCID -0.005; adversarial robustness 0.00254Hurt
Compress VGG-16 to 8.0% parameters (ablation)VGG-16 on CUB200-2011 · CUB200-2011 VGG-16 compressionadversarial robustness ||ε||₂: ΔCID -0.033; adversarial robustness 0.00109Hurt
Compress the network (ablation)VGG-16 on CUB200-2011 · CUB200-2011 compressionCIDHurt
Compress the network (ablation)VGG-16 on CUB200-2011 · CUB200-2011 compressionreconstruction capacityNo clear effect
Compress the network (ablation)VGG-16 on CUB200-2011 · CUB200-2011 compressionconcentrationNo clear effect
Train AlexNet with knowledge distillation (ablation)AlexNet on CUB200-2011 · CUB200-2011 classificationinformation discarding (CID)Hurt
Increase network depthDNNs for image classification and reconstruction · Image classification and image reconstructionCIDMixed
Use adversarial training (ablation)AlexNet on CUB-200 2011 · CUB-200 2011 classificationCIDImproved
Revise a VGG convolutional layer to use four 7×7×512 filters (ablation)VGG-16/VGG-19 · CUB200-2011 bird versus ImageNet random-image classificationCIDHurt

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