Improving VisNet for Object Recognition

TL;DR

This paper enhances the VisNet neural network model with biologically inspired modifications, significantly improving its ability to recognize objects and symmetries across various datasets, demonstrating robustness and biological plausibility.

Contribution

The study introduces novel variants of VisNet incorporating RBF neurons, Mahalanobis distance learning, and retinal preprocessing, advancing invariant object recognition capabilities.

Findings

Enhanced VisNet variants outperform baseline in recognition accuracy

Models effectively learn transformation-invariant features

Experimental validation across multiple datasets confirms robustness

Abstract

Object recognition plays a fundamental role in how biological organisms perceive and interact with their environment. While the human visual system performs this task with remarkable efficiency, reproducing similar capabilities in artificial systems remains challenging. This study investigates VisNet, a biologically inspired neural network model, and several enhanced variants incorporating radial basis function neurons, Mahalanobis distance based learning, and retinal like preprocessing for both general object recognition and symmetry classification. By leveraging principles of Hebbian learning and temporal continuity associating temporally adjacent views to build invariant representations. VisNet and its extensions capture robust and transformation invariant features. Experimental results across multiple datasets, including MNIST, CIFAR10, and custom symmetric object sets, show that these enhanced VisNet variants substantially improve recognition accuracy compared with the baseline model. These findings underscore the adaptability and biological relevance of VisNet inspired architectures, offering a powerful and interpretable framework for visual recognition in both neuroscience and artificial intelligence. Keywords: VisNet, Object Recognition, Symmetry Detection, Hebbian Learning, RBF Neurons, Mahalanobis Distance, Biologically Inspired Models, Invariant Representations