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

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.

References in corpus (2)

• Unsupervised Learning of Invariant Representations in Hierarchical Architectures
• Multi-View Priors for Learning Detectors from Sparse Viewpoint Data

Cited by in corpus (24)

• Deep Learning in Spiking Neural Networks
• Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks
• STDP-based spiking deep convolutional neural networks for object recognition
• Spiking Neural Networks Hardware Implementations and Challenges: a Survey
• First-spike based visual categorization using reward-modulated STDP
• S4NN: temporal backpropagation for spiking neural networks with one spike per neuron
• Deep learning incorporating biologically-inspired neural dynamics
• Deep Networks Can Resemble Human Feed-forward Vision in Invariant Object Recognition
• SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks with at most one Spike per Neuron
• BS4NN: Binarized Spiking Neural Networks with Temporal Coding and Learning
• Bio-Inspired Spiking Convolutional Neural Network using Layer-wise Sparse Coding and STDP Learning
• Unsupervised Visual Feature Learning with Spike-timing-dependent Plasticity: How Far are we from Traditional Feature Learning Approaches?
• Acquisition of Visual Features Through Probabilistic Spike-Timing-Dependent Plasticity
• Bio-Inspired Multi-Layer Spiking Neural Network Extracts Discriminative Features from Speech Signals
• Representation Learning using Event-based STDP
• Humans and deep networks largely agree on which kinds of variation make object recognition harder
• Artificial Intelligence-based algorithms in medical image scan seg-mentation and intelligent visual-content generation -- a concise overview
• Optimal localist and distributed coding of spatiotemporal spike patterns through STDP and coincidence detection
• Convolutional Spike Timing Dependent Plasticity based Feature Learning in Spiking Neural Networks
• Improving STDP-based Visual Feature Learning with Whitening
• A Deep Unsupervised Feature Learning Spiking Neural Network with Binarized Classification Layers for EMNIST Classification using SpykeFlow
• A temporal neural network model for object recognition using a biologically plausible decision making layer
• Enhancing efficiency of object recognition in different categorization levels by reinforcement learning in modular spiking neural networks
• A Microarchitecture Implementation Framework for Online Learning with Temporal Neural Networks