Attractive and Repulsive Perceptual Biases Naturally Emerge in Generative Adversarial Inference
Perceptual estimates exhibit a reversal in bias depending on uncertainty: they shift toward prior expectations under high stimulus noise, but away from them when sensory noise dominates. The normative framework of a Bayesian observer model can account for this phenomenon, yet most formulations treat it as given rather than explaining its emergence through learning. We introduce a Generative Adversarial Inference (GAI) network that acquires latent representations and inference strategies directly from sensory inputs, without hand-crafted likelihoods or priors. Trained using adversarial learning with reconstruction on Gabor stimuli under varying uncertainty, the network learns to recover underlying stimuli from noisy inputs, and spontaneously reproduces the bias reversal observed in human perception. This emergent behavior arises from network responses that reveal signatures of efficient coding and Bayesian inference. Our findings provide an end-to-end account of perceptual bias that unifies normative theory and deep learning.