Research map / Label-efficient and robust learning / Recognition and long-tail
Can Peripheral Representations Improve Clutter Metrics on Complex Scenes?
Arturo Deza, Miguel Eckstein
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 the PIFC eccentricity-dependent gain to Feature Congestion | Feature Congestion · Forced fixation search | hit-rate correlation (r): -0.19±0.13 -> -0.82±0.04 | Improved |
| Use an L2-norm rather than an L1-norm for PIFC (ablation) | FFC · Forced fixation search | hit-rate correlation (r): -0.82±0.04 -> -0.79±0.06 | No clear effect |
| Use KL-divergence rather than an L1-norm for PIFC (ablation) | FFC · Forced fixation search | hit-rate correlation (r): -0.82±0.04 -> -0.82±0.04 | No clear effect |
| Vary the PIFC ROI window from 4° to 12° (ablation) | FFC · Forced fixation search | hit-rate correlation (r): -0.80±0.04; -0.82±0.04; -0.81±0.05; -0.79±0.05; -0.76±0.06 | Mixed |
| Add a peripheral architecture to Edge Density | Edge Density · Forced fixation search | hit-rate correlation (r): -0.21 -> -0.76 | Improved |
| Add a peripheral architecture to Subband Entropy | Subband Entropy · Forced fixation search | hit-rate correlation (r): -0.19 -> -0.77 | Improved |
| Add a peripheral architecture to ProtoObject Segmentation | ProtoObject Segmentation · Forced fixation search | hit-rate correlation (r): -0.30 -> -0.74 | Improved |
| Use FFC instead of the Crowding Model | Forced fixation search · Forced fixation search | hit-rate correlation (r): -0.23±0.13 -> -0.82±0.04 | Improved |
Closest papers by meaning
- Seeing More with Less: Human-like Representations in Vision Models (CVPR 2025 · similarity 0.83)
- SeqRank: Sequential Ranking of Salient Objects (AAAI 2024 · similarity 0.83)
- See What You Are Told: Visual Attention Sink in Large Multimodal Models (ICLR 2025 · similarity 0.83)
- Gaze Target Detection by Merging Human Attention and Activity Cues (AAAI 2024 · similarity 0.82)
- Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers (CVPR 2024 · similarity 0.82)
- Beyond Accuracy: Tracking more like Human via Visual Search (NeurIPS 2024 · similarity 0.82)
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.
