Research map / Architectures and efficiency / CNN design
Diverse feature visualizations reveal invariances in early layers of deep neural networks
Santiago A. Cadena, Marissa A. Weis, Leon A. Gatys, Matthias Bethge, Alexander S. Ecker
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add diversity term (lambda>0) to activation maximization (ablation) | Hubel & Wiesel complex cell model · phase coverage of pre-images | coverage of invariant subspace: Four out of six solutions at lambda=0 are the globally best image | Improved |
| increase diversity weight lambda too far (lambda > 2) (ablation) | complex cell model · activation level | average activation | Hurt |
| train VGG-19 on ImageNet instead of random weights (ablation) | VGG-19 conv3_1 · invariance to diverse pre-images | image diversity at 90% activation: at least two and up to 100-fold | Improved |
| use ResNet-50 instead of VGG-19 | early layers · phase invariance | shift invariance index | Hurt |
| use ResNet-50 instead of VGG-19 | early layers · tolerance to local deformations | linear combination index | No clear effect |
| use minimum distance rather than average distance in diversity term (ablation) | diversity objective · Energy model coverage | phase coverage | Improved |
| go to higher layers within conv3 | VGG-19 · conv3 layers | shift invariance | Hurt |
Closest papers by meaning
- Stretching Beyond the Obvious: A Gradient-Free Framework to Unveil the Hidden Landscape of Visual Invariance (ICLR 2026 · similarity 0.90)
- Exploiting Invariance in Training Deep Neural Networks (AAAI 2022 · similarity 0.89)
- Learning Invariances in Neural Networks from Training Data (NeurIPS 2020 · similarity 0.89)
- Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with INNs (ECCV 2020 · similarity 0.88)
- From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication (ICLR 2024 · similarity 0.86)
- On Making $SE(2)$-Invariant Networks Optimal (NeurIPS 2026 · similarity 0.86)
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.
