Skip to main content
Advertisement

< Back to Article

The attentive reconstruction of objects facilitates robust object recognition

Fig 5

Results from ablating (-) ORA’s reconstruction-based spatial masking and feature binding components.

Leftmost bars in pink indicate the complete (no ablation) ORA model. Left: Recognition accuracy. Right: reaction time, approximated by the number of forward processing steps taken to recognize digits with confidence. Error bars are standard deviations from 5 different model runs. Asterisks (*) indicate statistical significance at a p-value of < 0.05 with Bonferroni corrections.

Fig 5

doi: https://doi.org/10.1371/journal.pcbi.1012159.g005