A model of saliency-based visual attention for rapid scene analysis¶
Why this mattered¶
TBD
Abstract¶
A visual attention system, inspired by the behavior and the neuronal architecture of the early primate visual system, is presented. Multiscale image features are combined into a single topographical saliency map. A dynamical neural network then selects attended locations in order of decreasing saliency. The system breaks down the complex problem of scene understanding by rapidly selecting, in a computationally efficient manner, conspicuous locations to be analyzed in detail.
Related¶
- cite → A feature-integration theory of attention — The saliency model operationalizes feature-integration theory by combining separate feature maps into a computational visual saliency map.
- enables → Robust Real-Time Face Detection — Saliency-based rapid scene analysis reinforced the idea of fast attentional feature selection that Viola-Jones implemented through efficient visual features.
- enables → Squeeze-and-Excitation Networks — Itti, Koch, and Niebur's saliency model formalized attention as selective feature weighting, enabling the channel-attention idea used in squeeze-and-excitation networks.
- enables → Rapid object detection using a boosted cascade of simple features — The saliency model's rapid attention-selection idea anticipates Viola-Jones's focus on fast candidate filtering before detailed recognition.
- cite ← Robust Real-Time Face Detection — Viola and Jones relate their attentional cascade to saliency-based visual attention as a way to focus computation on promising image regions.
- cite ← Squeeze-and-Excitation Networks — Squeeze-and-Excitation Networks connect to saliency-based visual attention through the idea of selectively emphasizing informative visual features.
- cite ← Rapid object detection using a boosted cascade of simple features — Viola-Jones connects to saliency-based attention through the goal of rapidly focusing computation on visually important image regions.
- enables ← A feature-integration theory of attention — Feature-integration theory linked attention to basic visual feature maps, which Itti, Koch, and Niebur computationalized as saliency maps for rapid scene analysis.