Deep Unsupervised Learning of Visual Similarities
This addresses the challenge of unsupervised visual similarity learning for computer vision applications, but it is incremental as it builds on existing deep learning frameworks.
The paper tackles the problem of unsupervised learning of visual similarities using deep learning, which is impaired by single positive samples and unreliable relationships, by proposing a method that groups similar samples and frames learning as a sequence of categorization tasks, achieving competitive performance on posture analysis and object classification.
Exemplar learning of visual similarities in an unsupervised manner is a problem of paramount importance to Computer Vision. In this context, however, the recent breakthrough in deep learning could not yet unfold its full potential. With only a single positive sample, a great imbalance between one positive and many negatives, and unreliable relationships between most samples, training of Convolutional Neural networks is impaired. In this paper we use weak estimates of local similarities and propose a single optimization problem to extract batches of samples with mutually consistent relations. Conflicting relations are distributed over different batches and similar samples are grouped into compact groups. Learning visual similarities is then framed as a sequence of categorization tasks. The CNN then consolidates transitivity relations within and between groups and learns a single representation for all samples without the need for labels. The proposed unsupervised approach has shown competitive performance on detailed posture analysis and object classification.