Ikshana: A Theory of Human Scene Understanding Mechanism.
Year: 2021
Type: preprint
Abstract: In recent years, deep neural networks (DNNs) achieved state-of-the-art performance on many computer vision tasks. However, the one typical drawback of these DNNs is the requirement of massive labeled data. Even though few-shot learning methods addressed this problem through metric-learning and meta-learning techniques, in this work, we address this problem from a neuroscience perspective. We propose a theory named Ikshana, to explain the functioning of the human brain, while humans understand an image. By following the Ikshana theory, we propose a novel neural-inspired CNN architecture named IkshanaNet for semantic segmentation. The empirical results demonstrate the effectiveness of our method on few data samples, outperforming several baselines, on the Cityscapes and the CamVid benchmarks.
Source: arXiv (Cornell University)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3125286341