Self-Calibrating Active Binocular Vision via Active Efficient Coding with Deep Autoencoders
This work addresses self-calibration in active vision systems, which is incremental as it builds on Active Efficient Coding with deep learning enhancements.
The paper tackled the problem of self-calibrating active binocular vision by developing a model that simultaneously learns visual representations, vergence, and pursuit eye movements using deep autoencoders and a new intrinsic motivation signal, demonstrating its performance in simulations.
We present a model of the self-calibration of active binocular vision comprising the simultaneous learning of visual representations, vergence, and pursuit eye movements. The model follows the principle of Active Efficient Coding (AEC), a recent extension of the classic Efficient Coding Hypothesis to active perception. In contrast to previous AEC models, the present model uses deep autoencoders to learn sensory representations. We also propose a new formulation of the intrinsic motivation signal that guides the learning of behavior. We demonstrate the performance of the model in simulations.