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

arXiv: https://arxiv.org/abs/1504.03871 · HTML: https://mlsanity.com/paper/1504.03871/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Apr 2015.

## Built on by (most cited first, 11 of 11)

- [Backpropagation with Biologically Plausible Spatio-Temporal Adjustment For Training Deep Spiking Neural Networks](https://mlsanity.com/paper/2110.08858/) (2021)
- [Spike time displacement based error backpropagation in convolutional spiking neural networks](https://mlsanity.com/paper/2108.13621/) (2021)
- [KLIF: An optimized spiking neuron unit for tuning surrogate gradient slope and membrane potential](https://mlsanity.com/paper/2302.09238/) (2023)
- [A Microarchitecture Implementation Framework for Online Learning with Temporal Neural Networks](https://mlsanity.com/paper/2105.13262/) (2021)
- [A noise based novel strategy for faster SNN training](https://mlsanity.com/paper/2211.05453/) (2022)
- [BioLCNet: Reward-modulated Locally Connected Spiking Neural Networks](https://mlsanity.com/paper/2109.05539/) (2021)
- [Enhancing efficiency of object recognition in different categorization levels by reinforcement learning in modular spiking neural networks](https://mlsanity.com/paper/2102.05401/) (2021)
- [SAR Image Classification Based on Spiking Neural Network through Spike-Time Dependent Plasticity and Gradient Descent](https://mlsanity.com/paper/2106.08005/) (2021)
- [Spike Agreement Dependent Plasticity: A scalable Bio-Inspired learning paradigm for Spiking Neural Networks](https://mlsanity.com/paper/2508.16216/) (2025)
- [Impact of Neuron Models on Spiking Neural Networks performance. A Complexity Based Classification Approach](https://mlsanity.com/paper/2509.06970/) (2025)
- [Human-AI Divergence in Ego-centric Action Recognition under Spatial and Spatiotemporal Manipulations](https://mlsanity.com/paper/2603.08317/) (2026)

## Abstract (arXiv)

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.