The mismatch negativity (MMN) component is an event-related potential (ERP) that can be elicited by any change in the acoustic environment, and it is related to memory-based, automatic processing mechanisms, and attentional capture processes. This component is well defined in the auditory modality. However, there is still a great controversy about its existence in the visual modality. This paper reviews the studies that are relevant with regard to memory-based, automatic deviance detection ERPs in the visual system. The paper discusses the main strengths and limitations of those studies and suggests what directions should be taken for future research.