The representation of object drawings and sketches in deep convolutional neural networks

no code implementations • NeurIPS Workshop SVRHM 2020 • Johannes Singer, Katja Seeliger, Martin N Hebart

Further, we show that a texture bias found in CNNs contributes both to the poor classification performance for drawings and the dissimilar representational structure, specifically in the later layers of the network.

Cultural Vocal Bursts Intensity Prediction Object