Brain-inspired automated visual object discovery and detection
| Autor: | Thomas Kailath, Vwani P. Roychowdhury, Lichao Chen, Sudhir Kumar Singh |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science 1.2 Psychological and socioeconomic processes Computer Vision and Pattern Recognition (cs.CV) cs.LG 0211 other engineering and technologies Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology computer.software_genre computer vision Machine Learning (cs.LG) Statistics - Machine Learning 0202 electrical engineering electronic engineering information engineering Invariant (mathematics) Associative property cs.CV Multidisciplinary Brain stat.ML machine learning PNAS Plus Pattern Recognition Visual Scalability Visual Perception Unsupervised learning 020201 artificial intelligence & image processing The Internet Mental health brain-inspired object models Visual Facial Recognition Algorithms brain memory models Machine Learning (stat.ML) Pattern Recognition Machine learning brain-inspired learning Contextual design Artificial Intelligence Underpinning research Humans Computer Simulation Eye Disease and Disorders of Vision 021110 strategic defence & security studies Markov chain business.industry Probabilistic logic Neurosciences Geographic Information Systems Artificial intelligence business computer Unsupervised Machine Learning |
| Zdroj: | Proceedings of the National Academy of Sciences of the United States of America, vol 116, iss 1 |
| Popis: | Despite significant recent progress, machine vision systems lag considerably behind their biological counterparts in performance, scalability, and robustness. A distinctive hallmark of the brain is its ability to automatically discover and model objects, at multiscale resolutions, from repeated exposures to unlabeled contextual data and then to be able to robustly detect the learned objects under various nonideal circumstances, such as partial occlusion and different view angles. Replication of such capabilities in a machine would require three key ingredients: ( i ) access to large-scale perceptual data of the kind that humans experience, ( ii ) flexible representations of objects, and ( iii ) an efficient unsupervised learning algorithm. The Internet fortunately provides unprecedented access to vast amounts of visual data. This paper leverages the availability of such data to develop a scalable framework for unsupervised learning of object prototypes—brain-inspired flexible, scale, and shift invariant representations of deformable objects (e.g., humans, motorcycles, cars, airplanes) comprised of parts, their different configurations and views, and their spatial relationships. Computationally, the object prototypes are represented as geometric associative networks using probabilistic constructs such as Markov random fields. We apply our framework to various datasets and show that our approach is computationally scalable and can construct accurate and operational part-aware object models much more efficiently than in much of the recent computer vision literature. We also present efficient algorithms for detection and localization in new scenes of objects and their partial views. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|