Abstract
The human brain has been a main source of inspiration for designing deep learning models. Recently, inspired by the specialized functions of two cerebral hemispheres in processing low and high spatial frequency information, some dual-path neural networks with global and local branches have been proposed to deal with both coarse- and fine-grained visual tasks simultaneously. However, in existing works, the interhemispheric communication mechanism, which is responded by the corpus callosum, the largest white matter structure in the human brain that connecting the left and right cerebral hemispheres, is still not fully explored and exploited. This paper aims to explore how the corpus callosum can inspire us to enable transfer and integration of information between global and local branches in hemisphere-inspired artificial neural networks, such that one branch can leverage the other's learned knowledge and benefit each other. To this end, we propose a gated intercommunication unit to selectively transfer useful knowledge between the two branches via attention mechanisms to alleviate the negative transfer. Experiments on sb-MNIST and two pedestrian attribute datasets show that the proposed method outperforms the compared ones in most cases.
Highlights
Neuroscience has long served as a source of inspiration for artificial intelligence (AI) [6]
A variety of deep learning models were inspired by biological neural networks [17], reinforcement learning was inspired by animal learning [38], visual attention mechanisms have been widely applied in emerging AI architectures [8], [13], [26], [42], [50], and spiking neural networks [22], [23], [29] are artificial neural networks (ANN) that more closely mimic natural neural networks
The mA of Two Pathway Network (TPN) is close to One Pathway Network (OPN); after plugging the cross-stitch units, the mA is improved around 1 point; while after using the Gated Intercommunication Units (GIU), the mA can be improved around 2% points for Dual Intercommunication Network (DIN)
Summary
Neuroscience has long served as a source of inspiration for artificial intelligence (AI) [6]. A variety of deep learning models were inspired by biological neural networks [17], reinforcement learning was inspired by animal learning [38], visual attention mechanisms have been widely applied in emerging AI architectures [8], [13], [26], [42], [50], and spiking neural networks [22], [23], [29] are artificial neural networks (ANN) that more closely mimic natural neural networks. We aim to explore how the corpus callosum, which connects the two cerebral hemispheres for transfer and integration of information between them, can inspire us to enable interhemispheric communications in hemisphere-inspired ANN for improved performance in computer vision tasks.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
