Embodied vision for learning object representations. (arXiv:2205.06198v1 [cs.LG])

Web: http://arxiv.org/abs/2205.06198

Recent time-contrastive learning approaches manage to learn invariant object
representations without supervision. This is achieved by mapping successive
views of an object onto close-by internal representations. When considering
this learning approach as a model of the development of human object
recognition, it is important to consider what visual input a toddler would
typically observe while interacting with objects. First, human vision is highly
foveated, with high resolution only available in the central region of the
field of view. Second, objects …

arxiv learning vision