Active Vision with Predictive Coding and Uncertainty Minimization

Abstract

We present an end-to-end procedure for embodied visual exploration based on two biologically inspired computations: predictive coding and uncertainty minimization. The procedure can be applied in a task-independent and intrinsically driven manner. We evaluate our approach on an active vision task, where an agent actively samples its visual environment to gather information. We show that our model builds unsupervised representations through exploration that allow it to efficiently categorize visual scenes. We further show that using these representations for downstream classification leads to superior data efficiency and learning speed compared to other baselines while maintaining lower parameter complexity. Finally, the modularity of our model allows us to probe its internal mechanisms and analyze the interaction between perception and action during exploratory behavior.