Unsupervised Deep Learning by Neighbourhood Discovery

by   Jiabo Huang, et al.

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.


page 6

page 8


Deep Feature Learning for Wireless Spectrum Data

In recent years, the traditional feature engineering process for trainin...

Learning Deep Representations for Scene Labeling with Semantic Context Guided Supervision

Scene labeling is a challenging classification problem where each input ...

Modelling Local Deep Convolutional Neural Network Features to Improve Fine-Grained Image Classification

We propose a local modelling approach using deep convolutional neural ne...

Deep Unsupervised Learning of Visual Similarities

Exemplar learning of visual similarities in an unsupervised manner is a ...

Unsupervised Representation Learning from Pathology Images with Multi-directional Contrastive Predictive Coding

Digital pathology tasks have benefited greatly from modern deep learning...

Deep Unsupervised Similarity Learning using Partially Ordered Sets

Unsupervised learning of visual similarities is of paramount importance ...

Please sign up or login with your details

Forgot password? Click here to reset