A neuromorphic model of the insect visual system for natural image processing

2026-02-06

AI Summary

This work proposes a neuromorphic model inspired by the insect visual system that integrates biologically plausible visual processing with self-supervised contrastive learning to enable unsupervised acquisition of sparse, discriminative representations—addressing a key limitation of conventional vision models that often neglect biological constraints. The approach offers dual implementations in both artificial neural networks (ANNs) and spiking neural networks (SNNs), producing stable sparse codes on benchmark datasets including flower recognition and natural images. Furthermore, in a simulated localization task, the model significantly outperforms a simple downsampling baseline, demonstrating the functional advantages of the proposed bio-inspired architecture for efficient, label-free representation learning.

Technology Category

• Computer Vision: Representation Learning for Vision
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Bio-inspired Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Insect vision supports complex behaviors including associative learning, navigation, and object detection, and has long motivated computational models for understanding biological visual processing. However, many contemporary models prioritize task performance while neglecting biologically grounded processing pathways. Here, we introduce a bio-inspired vision model that captures principles of the insect visual system to transform dense visual input into sparse, discriminative codes. The model is trained using a fully self-supervised contrastive objective, enabling representation learning without labeled data and supporting reuse across tasks without reliance on domain-specific classifiers. We evaluated the resulting representations on flower recognition tasks and natural image benchmarks. The model consistently produced reliable sparse codes that distinguish visually similar inputs. To support different modelling and deployment uses, we have implemented the model as both an artificial neural network and a spiking neural network. In a simulated localization setting, our approach outperformed a simple image downsampling comparison baseline, highlighting the functional benefit of incorporating neuromorphic visual processing pathways. Collectively, these results advance insect computational modelling by providing a generalizable bio-inspired vision model capable of sparse computation across diverse tasks.

Problem

• insect vision
• biologically grounded processing
• neuromorphic modeling
• sparse coding
• bio-inspired vision

Innovation

• neuromorphic vision
• self-supervised learning
• sparse coding
• spiking neural network
• insect-inspired model