Research map / Image generation / Autoregressive and latent generation
Emergence of foveal image sampling from learning to attend in visual scenes
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 learnable kernel positions and spreads to the fixed lattice (ablation) | Visual attention model · Cluttered MNIST Dataset 1 | classification error (%): 11.8 -> 5.1 | Helped |
| Add learnable kernel positions and spreads to the fixed lattice (ablation) | Visual attention model · Cluttered MNIST Dataset 2 | classification error (%): 31.9 -> 24.4 | Helped |
| Add zoom to the learnable translation-only lattice (ablation) | Visual attention model · Cluttered MNIST Dataset 1 | classification error (%): 5.1 -> 4.0 | Helped |
| Add zoom to the learnable translation-only lattice (ablation) | Visual attention model · Cluttered MNIST Dataset 2 | classification error (%): 24.4 -> 24.1 | No clear effect |
Closest papers by meaning
- Improved Efficiency Based on Learned Saccade and Continuous Scene Reconstruction From Foveated Visual Sampling (ICLR 2024 · similarity 0.87)
- Seeing More with Less: Human-like Representations in Vision Models (CVPR 2025 · similarity 0.87)
- A Unified Theory of Early Visual Representations from Retina to Cortex through Anatomically Constrained Deep CNNs (ICLR 2019 · similarity 0.86)
- Learned Region Sparsity and Diversity Also Predicts Visual Attention (NeurIPS 2016 · similarity 0.86)
- Flexible Context-Driven Sensory Processing in Dynamical Vision Models (NeurIPS 2024 · similarity 0.84)
- A Computational Framework for Modeling Emergence of Color Vision in the Human Brain (ICLR 2025 · similarity 0.84)
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.