Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Optimal visual search based on a model of target detectability in natural images
Shima Rashidi, Krista Ehinger, Andrew Turpin, Lars Kulik
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 |
|---|---|---|---|
| Replace logistic regression with MLP classifier on Alexnet features (ablation) | foveated detectability model · Detectability, 18 backgrounds | MSE vs human detectability: 0.0978 -> 0.256 | Hurt |
| Replace Alexnet with VGG19 features (logistic regression) (ablation) | foveated detectability model · Detectability, 18 backgrounds | MSE vs human detectability: 0.0978 -> 0.257 | Hurt |
| Replace Alexnet with luminance histogram features (ablation) | foveated detectability model · Detectability, 18 backgrounds | MSE vs human detectability: 0.0978 -> 0.3404 | Hurt |
| Replace Alexnet with HMAX features (ablation) | foveated detectability model · Detectability, 18 backgrounds | MSE vs human detectability: 0.0978 -> 0.224 | Hurt |
| Replace Alexnet with Textons (oriented filter banks) (ablation) | foveated detectability model · Detectability, 18 backgrounds | MSE vs human detectability: 0.0978 -> 0.2767 | Hurt |
| Use model detectabilities instead of human (oracle) detectabilities in ideal observer (ablation) | Bayesian ideal observer · Visual search, 18 backgrounds | number of fixations | No clear effect |
Closest papers by meaning
- ViSioNS: Visual Search in Natural Scenes Benchmark (NeurIPS 2022 · similarity 0.89)
- Visual Search Asymmetry: Deep Nets and Humans Share Similar Inherent Biases (NeurIPS 2021 · similarity 0.88)
- Eyegent: Visual Attention Orchestration on Concepts (IJCV 2026 · similarity 0.87)
- Target-Absent Human Attention (ECCV 2022 · similarity 0.86)
- Learned Region Sparsity and Diversity Also Predicts Visual Attention (NeurIPS 2016 · similarity 0.86)
- Beyond Accuracy: Tracking more like Human via Visual Search (NeurIPS 2024 · 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.
