Hybrid Primal Sketch: Combining Analogy, Qualitative Representations, and Computer Vision for Scene Understanding
This work addresses scene understanding for AI systems, but it appears incremental as it builds on Marr's Primal Sketch and existing components.
The paper tackles the problem of bridging sensor data with conceptual understanding in scene perception by developing the Hybrid Primal Sketch framework, which combines computer vision components with a high-level vision model to produce detailed shape and scene representations for data-efficient learning via analogical generalization.
One of the purposes of perception is to bridge between sensors and conceptual understanding. Marr's Primal Sketch combined initial edge-finding with multiple downstream processes to capture aspects of visual perception such as grouping and stereopsis. Given the progress made in multiple areas of AI since then, we have developed a new framework inspired by Marr's work, the Hybrid Primal Sketch, which combines computer vision components into an ensemble to produce sketch-like entities which are then further processed by CogSketch, our model of high-level human vision, to produce both more detailed shape representations and scene representations which can be used for data-efficient learning via analogical generalization. This paper describes our theoretical framework, summarizes several previous experiments, and outlines a new experiment in progress on diagram understanding.