Bio-inspired Unsupervised Learning of Visual Features Leads to Robust Invariant Object Recognition

TL;DR

This paper presents a bio-inspired, unsupervised spiking neural network model that significantly improves invariant object recognition, outperforming existing models on benchmark datasets by mimicking biological visual processing.

Contribution

The study introduces a novel asynchronous feedforward spiking neural network with biologically inspired architecture and learning rules, enhancing invariant object recognition capabilities.

Findings

Outperforms state-of-the-art models like DeepConvNet and HMAX.

Effectively recognizes objects under various appearance conditions.

Extracts highly informative, class-specific features.

Abstract

Retinal image of surrounding objects varies tremendously due to the changes in position, size, pose, illumination condition, background context, occlusion, noise, and nonrigid deformations. But despite these huge variations, our visual system is able to invariantly recognize any object in just a fraction of a second. To date, various computational models have been proposed to mimic the hierarchical processing of the ventral visual pathway, with limited success. Here, we show that the association of both biologically inspired network architecture and learning rule significantly improves the models' performance when facing challenging invariant object recognition problems. Our model is an asynchronous feedforward spiking neural network. When the network is presented with natural images, the neurons in the entry layers detect edges, and the most activated ones fire first, while neurons in higher layers are equipped with spike timing-dependent plasticity. These neurons progressively become selective to intermediate complexity visual features appropriate for object categorization. The model is evaluated on 3D-Object and ETH-80 datasets which are two benchmarks for invariant object recognition, and is shown to outperform state-of-the-art models, including DeepConvNet and HMAX. This demonstrates its ability to accurately recognize different instances of multiple object classes even under various appearance conditions (different views, scales, tilts, and backgrounds). Several statistical analysis techniques are used to show that our model extracts class specific and highly informative features.