Skip to main content
Advertisement

< Back to Article

Hierarchical abstraction drives human-like 3-D shape processing in deep learning models

Fig 10

Recognition performance of humans and models under scrambling manipulations.

Top panel, Human classification accuracy for intact and scrambled point clouds. Middle panel, DGCNN model accuracy for intact and scrambled point clouds. Bottom panel, Point Transformer model accuracy. Error bars represent 95% confidence intervals around the mean accuracy, estimated across participants for human performance and across stimuli for model performance.

Fig 10

doi: https://doi.org/10.1371/journal.pcbi.1014047.g010