Authors:
George Galanakis
1
;
2
;
Xenophon Zabulis
2
and
Antonis Argyros
1
;
2
Affiliations:
1
Computer Science Department, University of Crete, Greece
;
2
Institute of Computer Science, FORTH, Greece
Keyword(s):
Label Noise, Data Denoising, Deep Metric Learning, KNN, Image Retrieval.
Abstract:
The effectiveness of supervised deep metric learning relies on the availability of a correctly annotated dataset, i.e., a dataset where images are associated with correct class labels. The presence of incorrect labels in a dataset disorients the learning process. In this paper, we propose an approach to combat the presence of such label noise in datasets. Our approach operates online, during training and on the batch level. It examines the neighborhood of samples, considers which of them are noisy and eliminates them from the current training step. The neighborhood is established using features obtained from the entire dataset during previous training epochs and therefore is updated as the model learns better data representations. We evaluate our approach using multiple datasets and loss functions, and demonstrate that it performs better or comparably to the competition. At the same time, in contrast to the competition, it does not require knowledge of the noise contamination rate of
the employed datasets.
(More)