AI Paper Atlas

Research map / Image generation / Image restoration

A Tour of Convolutional Networks Guided by Linear Interpreters

Pablo Navarrete Michelini, Hanwen Liu, Yunhua Lu, Xingqun Jiang

ICCV 2019 · Image generation › Image restoration · approach: Inverse imaging with learned priors · 8 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
use a larger or better ImageNet classifier family member (e.g. VGG-11 to VGG-19)VGG classifiers · ImageNet-1k valaverage residual contribution to top-1 score (%): 82.2% -> 85.5%Improved
use DenseNet-161 instead of AlexNetclassification CNNs · ImageNet-1k valaverage residual contribution to top-1 score (%): 78.5% -> 95.0%Improved
use ResNet-152 instead of ResNet-34ResNet classifiers · ImageNet-1k valaverage residual contribution to top-1 score (%): 83.7% -> 81.1%No clear effect
add batch normalization to VGG trainingVGG-19 · ImageNet-1k vallayer-wise bias contributions: 85.5% -> 85.8%Mixed
replace storing activations (DFV) with LinearScope extra batchlinear interpreter · speedspeedup: 2x to 10^4x speedup over DFVImproved
apply FGSM adversarial noise to inputsVGG classifiers · ImageNet-1k vallayer-wise contributions and pixel votesHurt

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