A brain-inspired object-based attention network for multiobject recognition and visual reasoning
Open Access
- 2 May 2023
- journal article
- research article
- Published by Association for Research in Vision and Ophthalmology (ARVO) in Journal of Vision
- Vol. 23 (5) , 16
Abstract
The visual system uses sequences of selective glimpses to objects to support goal-directed behavior, but how is this attention control learned? Here we present an encoder–decoder model inspired by the interacting bottom-up and top-down visual pathways making up the recognition-attention system in the brain. At every iteration, a new glimpse is taken from the image and is processed through the “what” encoder, a hierarchy of feedforward, recurrent, and capsule layers, to obtain an object-centric (object-file) representation. This representation feeds to the “where” decoder, where the evolving recurrent representation provides top-down attentional modulation to plan subsequent glimpses and impact routing in the encoder. We demonstrate how the attention mechanism significantly improves the accuracy of classifying highly overlapping digits. In a visual reasoning task requiring comparison of two objects, our model achieves near-perfect accuracy and significantly outperforms larger models in generalizing to unseen stimuli. Our work demonstrates the benefits of object-based attention mechanisms taking sequential glimpses of objects.Keywords
This publication has 66 references indexed in Scilit:
- How Does the Brain Solve Visual Object Recognition?Neuron, 2012
- A century of Gestalt psychology in visual perception: I. Perceptual grouping and figure–ground organization.Psychological Bulletin, 2012
- Comparing machines and humans on a visual categorization testProceedings of the National Academy of Sciences, 2011
- Attention, Intention, and Priority in the Parietal LobeAnnual Review of Neuroscience, 2010
- What and where pathwaysScholarpedia, 2008
- Tracking Multiple Items Through Occlusion: Clues to Visual ObjecthoodCognitive Psychology, 1999
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Figure-ground organization and object recognition processes: An interactive account.Journal of Experimental Psychology: Human Perception and Performance, 1998
- ‘What’ and ‘where’ in the human brainCurrent Opinion in Neurobiology, 1994
- Infant Chimpanzees Spontaneously Perceive Both Concrete and Abstract Same/Different RelationsChild Development, 1990