25 Years of CNNs: Can We Compare to Human Abstraction Capabilities?
We try to determine the progress made by convolutional neural networks over the past 25 years in classifying images into abstract classes. For this purpose we compare the performance of LeNet to that of GoogLeNet at classifying randomly generated images which are differentiated by an abstract property (e.g., one class contains two objects of the same size, the other class two objects of different sizes). Our results show that there is still work to do in order to solve vision problems humans are able to solve without much difficulty.
KeywordsConvolutional neural networks Abstract classes Abstract reasoning
We want to thank nVidia for supporting this research with their “NVIDIA Hardware Grant”. We also want to thank Franois Fleuret for providing us with the dataset used in this paper.
- 2.Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar
- 4.Bongard, M.M.: Pattern Recognition. Spartan Books (1970)Google Scholar
- 5.Hofstadter, D.R.: Gödel, escher, bach: an eternal golden braid (1979)Google Scholar
- 6.Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: Convolutional architecture for fast feature embedding (2014) arXiv preprint: arXiv:1408.5093
- 7.Kingma, D., Ba, J.: Adam: A method for stochastic optimization (2014). arXiv preprint: arXiv:1412.6980
- 8.Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions (2014). arXiv preprint: arXiv:1409.4842