 |
    |
Analyzing the Performance of Multilayer Neural Networks for Object Recognition
Pulkit Agrawal, Ross Girshick, and Jitendra Malik
University of California, Berkeley, USApulkitag@eecs.berkeley.edu
rbg@eecs.berkeley.edu
malik@eecs.berkeley.edu
Abstract. In the last two years, convolutional neural networks (CNNs) have achieved an impressive suite of results on standard recognition datasets and tasks. CNN-based features seem poised to quickly replace engineered representations, such as SIFT and HOG. However, compared to SIFT and HOG, we understand much less about the nature of the features learned by large CNNs. In this paper, we experimentally probe several aspects of CNN feature learning in an attempt to help practitioners gain useful, evidence-backed intuitions about how to apply CNNs to computer vision problems.
Keywords: convolutional neural networks, object recognition, empirical analysis
LNCS 8695, p. 329 ff.
lncs@springer.com
© Springer International Publishing Switzerland 2014