Abstract
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.
Item Type: | Journal article |
---|---|
Form of publication: | Publisher's Version |
Faculties: | History and Art History > Department of Art History > Art History |
Subjects: | 000 Computer science, information and general works > 000 Computer science, knowledge, and systems 700 Arts and recreation > 700 Arts |
ISSN: | 0031-3203 |
Language: | English |
Item ID: | 109776 |
Date Deposited: | 21. Mar 2024, 10:02 |
Last Modified: | 28. May 2024, 12:40 |