Deep convolutional neural networks (CNNs) have demonstrated remarkable success in computer vision by supervisedly learning strong visual feature representations. However, training CNNs relies heavily on the availability of exhaustive training data annotations, limiting significantly their deployment and scalability in many application scenarios. In this work, we introduce a generic unsupervised deep learning approach to training deep models without the need for any manual label supervision. Specifically, we progressively discover sample anchored/centred neighbourhoods to reason and learn the underlying class decision boundaries iteratively and accumulatively. Every single neighbourhood is specially formulated so that all the member samples can share the same unseen class labels at high probability for facilitating the extraction of class discriminative feature representations during training. Experiments on image classification show the performance advantages of the proposed method over the state-of-the-art unsupervised learning models on six benchmarks including both coarse-grained and fine-grained object image categorisation.
Jiabo Huang (Queen Mary University of London)
Jiabo (Raymond) Huang is currently a first-year PhD student within the Computer Vision Group in the School of Electronic Engineering and Computer Science at Queen Mary, University of London, supervised by Prof. Shaogang (Sean) Gong. His current research is mainly in Unsupervised Deep Learning.
Qi Dong (Queen Mary University of London)
Shaogang Gong (Queen Mary University of London)
Xiatian Zhu (Vision Semantics Limited)
Related Events (a corresponding poster, oral, or spotlight)
2019 Oral: Unsupervised Deep Learning by Neighbourhood Discovery »
Thu Jun 13th 11:35 -- 11:40 PM Room Room 104