AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Unlocking Feature Visualization for Deep Network with MAgnitude Constrained Optimization

Thomas FEL, Thibaut Boissin, Victor Boutin, Agustin Martin Picard, Paul Novello, Julien Colin, Drew Linsley, Tom ROUSSEAU, Remi Cadene, Lore Goetschalckx, Laurent Gardes, Thomas Serre

NeurIPS 2023 · Image generation › Autoregressive and latent generation · approach: Classical generative image synthesis

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 magnitude-constrained phase optimization instead of Fourier optimizationFeature visualization · FlexiViT, ViT, and ResNetV2plausibility score (1-KNN): 1815 -> 1473; 1817 -> 1097; 1837 -> 1248Improved
Use magnitude-constrained phase optimization instead of Fourier optimizationFeature visualization · FlexiViT, ViT, and ResNetV2FID: 250.25 -> 230.68; 257.81 -> 241.68; 318.15 -> 312.66Improved
Remove transparency mask (ablation)MACO · FlexiViTplausibility: 571.68 -> 617.9 (+46.2)Hurt
Remove transparency mask (ablation)MACO · FlexiViTFID: 211.0 -> 208.1 (-2.9)No clear effect
Remove random crop augmentation (ablation)MACO · FlexiViTplausibility: 571.68 -> 680.1 (+62.2)Hurt
Remove random crop augmentation (ablation)MACO · FlexiViTFID: 211.0 -> 299.2 (-91.1)Hurt
Remove random crop augmentation (ablation)MACO · FlexiViTlogit magnitude: 5.12 -> 8.18 (+3.1)Improved
Remove additive noise augmentation (ablation)MACO · FlexiViTplausibility: 571.68 -> 707.3 (+27.1)Hurt
Remove additive noise augmentation (ablation)MACO · FlexiViTFID: 211.0 -> 324.5 (-25.3)Hurt
Remove additive noise augmentation (ablation)MACO · FlexiViTlogit magnitude: 5.12 -> 11.7 (+3.5)Improved
Show MACO visualization instead of Olah visualizationHuman prediction of model-favored query · VGG16, ResNet50, and ViTlogodds of correct query choice: 0.43, SE=0.13, z=3.31, p=.005; 0.66, SE=0.13, z=4.99, p<.0001Improved
Add MACO visualization to the no-visualization controlHuman prediction of model-favored query · VGG16, ResNet50, and ViTlogodds of correct query choice: 0.69, SE=0.13, z=5.38, p<.0001; 0.92, SE=0.13, z=7.07, p<.0001Improved

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