Research map / Vision-language and multimodal / Human and embodied modeling
Prune and distill: similar reformatting of image information along rat visual cortex and deep neural networks
Paolo Muratore, Sina Tafazoli, Eugenio Piasini, Alessandro Laio, Davide Zoccolan
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 |
|---|---|---|---|
| train VGG-16 on ImageNet vs random weights | VGG-16 · luminosity information in first layer | normalized single-unit information | Improved |
| train VGG-16 on ImageNet vs random weights | VGG-16 · contrast information in early layers | normalized single-unit information | Improved |
| train VGG-16 vs random weights, late layers | VGG-16 · contrast information in late layers | normalized single-unit information | Hurt |
| train VGG-16 vs random weights | VGG-16 · orientation information, conv layers | normalized single-unit information | Improved |
| train VGG-16 vs random weights | VGG-16 · corner information, conv layers | normalized single-unit information | Improved |
| hybrid network: trained layers up to l*, random layers after (ablation) | VGG-16 · luminosity information | normalized single-unit information | Hurt |
| hybrid network: random layers after l* (ablation) | VGG-16 · contrast information | normalized single-unit information | Mixed |
| train VGG-16 vs random weights | VGG-16 · category information, ImageNet test images | normalized single-unit information | Improved |
| train VGG-16 vs random weights | VGG-16 linear SVM readout · 10 ImageNet categories | decoding accuracy | Mixed |
Closest papers by meaning
- Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representations (ICLR 2025 · similarity 0.89)
- Sparse components distinguish visual pathways & their alignment to neural networks (ICLR 2025 · similarity 0.89)
- A Convolutional Neural Network Interpretable Framework for Human Ventral Visual Pathway Representation (AAAI 2024 · similarity 0.88)
- In Silico Mapping of Visual Categorical Selectivity Across the Whole Brain (NeurIPS 2025 · similarity 0.87)
- Parallel Backpropagation for Shared-Feature Visualization (NeurIPS 2024 · similarity 0.87)
- Bridging Critical Gaps in Convergent Learning: How Representational Alignment Evolves Across Layers, Training, and Distribution Shifts (NeurIPS 2025 · similarity 0.87)
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.
