After-effects and the reach of perceptual content

In this paper, I discuss the use of after-effects as a criterion for showing that we can perceive high-level properties. According to this criterion, if a high-level property (for example, an emotional expression) is susceptible to after-effects, this suggests that the property can be perceived, rather than cognized. The defenders of the criterion claim that, since after-effects are also present for low-level, uncontroversially perceptual properties (such as orientation), we can safely infer that high-level after-effects are perceptual as well. The critics of the criterion, on the other hand, assimilate it to superficially similar effects in cognition (such as decision biases) and argue that the after-effect criterion is a cognitive phenomenon rather than a perceptual one, and that as a result it is not a reliable guide for exploring the contents of perception. I argue against both of these views and show that high-level after-effects cannot be identified either with low-level after-effects or with cognitive biases. I suggest an intermediate position: high-level after-effects are not cognitive, but they are nonetheless not a good criterion for exploring the contents of perception.