AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Principal Feature Visualisation in Convolutional Neural Networks

Marianne Bakken, Johannes Kvam, Alexey A. Stepanov, Asbjørn Berge

ECCV 2020 · Architectures and efficiency › CNN design · approach: Filter design and trained-filter analysis · 2 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
weight upsampled principal feature map with summed earlier-layer activation maps (ablation)PFV on VGG16 · dog and cat batch (qualitative)visual background suppressionImproved
use a single-image batch instead of a mixed-class batch (ablation)PFV · dog and cat images (qualitative)feature granularityMixed
randomise network weights (untrained VGG16) (ablation)PFV · sanity check, qualitativevisualisation similarity to trained modelHurt
restrict the batch to five similar animal classes instead of 20 diverse classes (ablation)PFV on VGG16 · Pascal VOC2012 (qualitative)separation of cats and dogs from other animalsImproved
use weak PFV feature response as a predictor of poor fine-tuned accuracyVGG16 fine-tuned on VOC2012 · chair, table, sofa classesper-class accuracy: table 54, sofa 73, chair 73 versus cat 95Improved

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