We Don't Need No Annotation: Efficient Training for Image Retrieval
Ondrej Chum, Czech Technical University, Prague
Abstract:
Convolutional Neural Networks (CNNs) achieve the state-of-theart
performance in many computer vision tasks. However, this achievement
is preceded by extreme manual annotation in order to perform
either training from scratch or fine-tuning for the target task. In the
talk, I will address CNN fine-tuning for image retrieval and related
tasks in a fully automated manner.