Proceedings

Unsupervised Learning on Neural Network Outputs: With Application in Zero-Shot Learning

Yao Lu

Download BibTeX Cite

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 3432-3437.

Abstract

The outputs of a trained neural network contain much richer information than just a one-hot classifier. For example, a neural network might give an image of a dog the probability of one in a million of being a cat but it is still much larger than the probability of being a car. To reveal the hidden structure in them, we apply two unsupervised learning algorithms, PCA and ICA, to the outputs of a deep Convolutional Neural Network trained on the ImageNet of 1000 classes. The PCA/ICA embedding of the object classes reveals their visual similarity and the PCA/ICA components can be interpreted as common visual features shared by similar object classes. For an application, we proposed a new zero-shot learning method, in which the visual features learned by PCA/ICA are employed. Our zero-shot learning method achieves the state-of-the-art results on the ImageNet of over 20000 classes.

Yao Lu. 2016. Unsupervised Learning on Neural Network Outputs: With Application in Zero-Shot Learning. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16. IJCAI, 3432–3437. https://ijcai.org/proceedings/2016/485
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards