Biomimetic visual recognition at low resolution with continuous learning

Despite the tremendous advancements achieved in the field of artificial intelligence (AI) in the past decade, there are tasks where AI systems lag behind their biological counterparts. Here, we propose to combine insights gained through the study of biological active perception and state-of-the-art AI, together with specialized biomimetic hardware, to bridge this gap. Specifically, we propose to develop an efficient video-based visual recognition system capable of continuous learning. The development will exploit the expertise of MBZUAI and WIS groups via an extensive collaboration, using the following steps: Designing a vision transformers-based active perception system for low-resolution visual recognition, adding a dynamic-recurrent front-end module; adapting the system for continuous learning scenarios; and enabling performance using an event-based visual input.