For object recognition convolutional neural networks, the shape bias leads to greater robustness against style and pattern change distraction.

Current deep-learning models for object recognition are known to be heavily biased toward texture. In contrast, human visual systems are known to be biased toward shape and structure. What could be the design principles in human visual systems that led to this difference? How could we introduce more shape bias into the deep learning models? In this paper, we report that sparse coding, a ubiquitous principle in the brain, can in itself introduce shape bias into the network.

What spatial frequency information do humans and neural networks use to recognize objects? In neuroscience, critical band masking is an established tool that can reveal the frequency-selective filters used for object recognition. Critical band masking measures the sensitivity of recognition performance to noise added at each spatial frequency. Existing critical band masking studies show that humans recognize periodic patterns (gratings) and letters by means of a spatial-frequency filter (or channel) that has a frequency bandwidth of one octave (doubling of frequency). Here, we introduce critical band masking as a task for network-human comparison and test 14 humans and 76 neural networks on 16-way ImageNet categorization in the presence of narrowband noise.

The supplementary material is structured as follows. We start with terminology in Section S.1, afterwards we In addition to method details, we provide extended experimental results in Figure SF.3 (error consistency of all Furthermore, Figure SF.4 visualises qualitative error differences by plotting which stimuli were particularly easy We would like to briefly clarify the name error consistency . Two decision makers necessarily show some degree of consistency due to chance agreement. How much observed consistency can we expect at most for a given expected consistency? We distinguish between two cases.

Higher learning rates produce greater shape bias. As shown in Figure A.1, higher values of learning rate and weight decay were associated with greater We found that random-crop augmentation biases models towards texture (Section 5). We did not change the aspect ratio or other data augmentation settings. Networks with limited receptive fields learn texture more easily than shape. Shape is persistently more decodable through the convolutional layers of AlexNet than is texture, which rises through them.

However, all objectives and architectures still lead to models that make texture-based classification decisions a majority of the time, even if shape information is decodable from their hidden representations. The effect of data augmentation is much larger.

Across humans and all 76 networks, we were able to obtain good fits (with low standard error) for all 3 parameters.