Gaze following requires early visual experience

Abstract

SignificanceEarly in life, humans spontaneously learn to extract complex visual information without external guidance. Current vision models fail to replicate such learning, relying instead on extensive supervision. A classic example is gaze understanding, an early-learned skill useful for joint attention and social interaction. We studied gaze understanding in children who recovered from early-onset near-complete blindness through late cataract surgery. Following treatment, they acquired sufficient visual acuity for detailed pattern recognition, but they failed to develop automatic gaze following. Our computational modeling suggests that their learning is severely limited due to reduced availability of internal self-supervision mechanisms, which guide learning in normal development. The results have implications to understanding natural visual learning, potential rehabilitation, and obtaining unsupervised learning in vision models.