Format

Send to

Choose Destination
Proc Natl Acad Sci U S A. 2019 Jan 2;116(1):96-105. doi: 10.1073/pnas.1802103115. Epub 2018 Dec 17.

Brain-inspired automated visual object discovery and detection.

Author information

1
Department of Electrical and Computer Engineering, University of California, Los Angeles, CA 90095.
2
Department of Electrical Engineering, Stanford University, Stanford, CA 94305 kailath@stanford.edu vwani@ucla.edu.
3
Department of Electrical and Computer Engineering, University of California, Los Angeles, CA 90095; kailath@stanford.edu vwani@ucla.edu.

Abstract

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.

KEYWORDS:

brain memory models; brain-inspired learning; brain-inspired object models; computer vision; machine learning

PMID:
30559207
PMCID:
PMC6320548
[Available on 2019-07-02]
DOI:
10.1073/pnas.1802103115

Conflict of interest statement

The authors declare no conflict of interest.

Supplemental Content

Full text links

Icon for HighWire
Loading ...
Support Center