Mining on Manifolds: Metric Learning Without Labels

Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondřej Chum; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 7642-7651

Abstract


In this work we present a novel unsupervised framework for hard training example mining. The only input to the method is a collection of images relevant to the target application and a meaningful initial representation, provided e.g. by pre-trained CNN. Positive examples are distant points on a single manifold, while negative examples are nearby points on different manifolds. Both types of examples are revealed by disagreements between Euclidean and manifold similarities. The discovered examples can be used in training with any discriminative loss. The method is applied to unsupervised fine-tuning of pre-trained networks for fine-grained classification and particular object retrieval. Our models are on par or are outperforming prior models that are fully or partially supervised.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Iscen_2018_CVPR,
author = {Iscen, Ahmet and Tolias, Giorgos and Avrithis, Yannis and Chum, Ondřej},
title = {Mining on Manifolds: Metric Learning Without Labels},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}