Assessing Shape Bias Property of Convolutional Neural Networks

by   Hossein Hosseini, et al.

It is known that humans display "shape bias" when classifying new items, i.e., they prefer to categorize objects based on their shape rather than color. Convolutional Neural Networks (CNNs) are also designed to take into account the spatial structure of image data. In fact, experiments on image datasets, consisting of triples of a probe image, a shape-match and a color-match, have shown that one-shot learning models display shape bias as well. In this paper, we examine the shape bias property of CNNs. In order to conduct large scale experiments, we propose using the model accuracy on images with reversed brightness as a metric to evaluate the shape bias property. Such images, called negative images, contain objects that have the same shape as original images, but with different colors. Through extensive systematic experiments, we investigate the role of different factors, such as training data, model architecture, initialization and regularization techniques, on the shape bias property of CNNs. We show that it is possible to design different CNNs that achieve similar accuracy on original images, but perform significantly different on negative images, suggesting that CNNs do not intrinsically display shape bias. We then show that CNNs are able to learn and generalize the structures, when the model is properly initialized or data is properly augmented, and if batch normalization is used.


page 2

page 3

page 5


Increasing Shape Bias in ImageNet-Trained Networks Using Transfer Learning and Domain-Adversarial Methods

Convolutional Neural Networks (CNNs) have become the state-of-the-art me...

Convolutional Neural Networks Rarely Learn Shape for Semantic Segmentation

Shape learning, or the ability to leverage shape information, could be a...

Background Invariant Classification on Infrared Imagery by Data Efficient Training and Reducing Bias in CNNs

Even though convolutional neural networks can classify objects in images...

25 years of CNNs: Can we compare to human abstraction capabilities?

We try to determine the progress made by convolutional neural networks o...

On the Limitation of Convolutional Neural Networks in Recognizing Negative Images

Convolutional Neural Networks (CNNs) have achieved state-of-the-art perf...

Frustratingly Simple Domain Generalization via Image Stylization

Convolutional Neural Networks (CNNs) show impressive performance in the ...

The Emergence of the Shape Bias Results from Communicative Efficiency

By the age of two, children tend to assume that new word categories are ...

Please sign up or login with your details

Forgot password? Click here to reset