Subitizing with Variational Autoencoders
This work addresses the challenge of unsupervised learning of numerosity in computer vision, which is incremental as it builds on prior findings but applies to more complex natural images.
The paper tackled the problem of enabling neural networks to spontaneously perform subitizing (identifying numerosity in small sets) from complex natural images without supervision, using variational autoencoders trained on the Salient Object Subitizing dataset, and found that the networks learned to encode numerosity as a basic visual property with invariance to object area.
Numerosity, the number of objects in a set, is a basic property of a given visual scene. Many animals develop the perceptual ability to subitize: the near-instantaneous identification of the numerosity in small sets of visual items. In computer vision, it has been shown that numerosity emerges as a statistical property in neural networks during unsupervised learning from simple synthetic images. In this work, we focus on more complex natural images using unsupervised hierarchical neural networks. Specifically, we show that variational autoencoders are able to spontaneously perform subitizing after training without supervision on a large amount images from the Salient Object Subitizing dataset. While our method is unable to outperform supervised convolutional networks for subitizing, we observe that the networks learn to encode numerosity as basic visual property. Moreover, we find that the learned representations are likely invariant to object area; an observation in alignment with studies on biological neural networks in cognitive neuroscience.