{"type":"ScholarlyArticle","title":"Unsupervised Learning on Neural Network Outputs: With Application in Zero-Shot Learning","authors":[{"name":"Yao Lu","slug":"yao-lu","given":"Yao","family":"Lu","affiliation":""}],"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.","doi":null,"url":"https://ijcai.org/proceedings/2016/485","pdf":"https://ijcai.org/proceedings/2016/0485.pdf","markdown":"https://ijcai.org/proceedings/2016/485.md","bibtex":"https://ijcai.org/proceedings/2016/bibtex/485","volume":{"slug":"2016","title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2016","url":"https://ijcai.org/proceedings/2016/","year":2016,"location":"New York, NY, USA","dates":"9–15 July 2016","editors":"Subbarao Kambhampati","isbn":"978-1-57735-770-4; 978-1-57735-771-1","publisher":"AAAI Press / International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":485,"pages":{"first":3432,"last":3437},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}