Authors
Scott Reed, Honglak Lee, Dragomir Anguelov, Christian Szegedy, Dumitru Erhan, Andrew Rabinovich
Publication date
2015
Journal
ArXiv e-prints
Description
Abstract: Current state-of-the-art deep learning systems for visual object recognition and
detection use purely supervised training with regularization such as dropout to avoid
overfitting. The performance depends critically on the amount of labeled examples, and in
current practice the labels are assumed to be unambiguous and accurate. However, this
assumption often does not hold; eg in recognition, class labels may be missing; in detection,
objects in the image may not be localized; and in general, the labeling may be subjective. ...
detection use purely supervised training with regularization such as dropout to avoid
overfitting. The performance depends critically on the amount of labeled examples, and in
current practice the labels are assumed to be unambiguous and accurate. However, this
assumption often does not hold; eg in recognition, class labels may be missing; in detection,
objects in the image may not be localized; and in general, the labeling may be subjective. ...
Total citations
Scholar articles
S Reed, H Lee, D Anguelov, C Szegedy, D Erhan… - arXiv preprint arXiv:1412.6596, 2014
Dates and citation counts are estimated and are determined automatically by a computer program.