An Avian-Inspired Computational Model Driven by Texture-Color Prioritization Strategies in Visual Processing

Birds have evolved distinctive visual processing strategies to adapt to complex natural environments. Pigeons can discriminate visual objects using multiple cues, including local texture, color, and shape. However, natural objects contain these cues simultaneously, and it remains unclear how the pigeon visual system balances these visual features when they co-occur. Whether such biological feature-prioritization principles can inform computational recognition models also remains unknown. Here, we combined behavioral delayed matching-to-sample tasks, in vivo electrophysiological recordings from the entopallium, and spectral-coherence-based network analysis to investigate multidimensional visual processing in pigeons. Behavioral and electrophysiological results revealed a stable feature-prioritization pattern dominated by color and texture, with shape playing a subordinate role. Functional connectivity further indicated that network organization became sparser under information-rich conditions, suggesting that pigeons selectively extract nonredundant cues rather than processing all dimensions equally. Guided by these biological findings, the present research developed the Avian-inspired Feature Gating Model (AFGM). By incorporating independent channel gating and sparse regularization, AFGM formalizes this biological feature-weighting strategy. The model achieved a modest performance advantage over the HVE baseline on fine-grained recognition tasks. Together, these results reveal a consistent texture-color prioritization pattern in pigeons and provide a biologically inspired framework for feature-weighted machine vision.