A neuromorphic model of the insect visual system for natural image processing
This work addresses the need for bio-inspired vision models that incorporate neuromorphic pathways for tasks like object detection and navigation, though it appears incremental in advancing insect computational modelling.
The researchers tackled the problem of creating a biologically grounded model of insect vision for natural image processing, resulting in a model that produced reliable sparse codes and outperformed a baseline in a simulated localization setting.
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.