The attentive reconstruction of objects facilitates robust object recognition
Fig 7
ORA often hallucinates a non-existing pattern out of noise, and these errors are perceived as more likely by humans compared to errors made by our CNN baseline.
A: Example of ORA’s explain-way behavior and the resulting errors in classification. B: Two alternative forced choice experimental procedure requiring participants to choose which of two model predictions, one from ORA and the other from our CNN baseline (but both errors), is the more plausible human interpretation of the corrupted digit. C: The relative likelihood of ORA’s errors being perceived as more like those from a human, quantified as an odds ratio (a higher value indicates a more plausible ORA error). Error bars indicate standard errors, and asterisks (*) indicate odds ratios greater than 1 at a significance level of p < 0.05.