TY - GEN
T1 - Split-brain autoencoders
T2 - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
AU - Zhang, Richard Yi
AU - Isola, Phillip
AU - Efros, Alexei A.
N1 - We thank members of the Berkeley Artificial Intelligence Research Lab (BAIR), in particular Andrew Owens, for helpful discussions, as well as Saurabh Gupta for help with RGB-D experiments. This research was supported, in part, by Berkeley Deep Drive (BDD) sponsors, hardware donations by NVIDIA Corp and Algorithmia, an Intel research grant, NGA NURI, and NSF SMA-1514512. Thanks Obama.
PY - 2017/11/6
Y1 - 2017/11/6
N2 - We propose split-brain autoencoders, a straightforward modification of the traditional autoencoder architecture, for unsupervised representation learning. The method adds a split to the network, resulting in two disjoint sub-networks. Each sub-network is trained to perform a difficult task - predicting one subset of the data channels from another. Together, the sub-networks extract features from the entire input signal. By forcing the network to solve cross-channel prediction tasks, we induce a representation within the network which transfers well to other, unseen tasks. This method achieves state-of-the-art performance on several large-scale transfer learning benchmarks.
AB - We propose split-brain autoencoders, a straightforward modification of the traditional autoencoder architecture, for unsupervised representation learning. The method adds a split to the network, resulting in two disjoint sub-networks. Each sub-network is trained to perform a difficult task - predicting one subset of the data channels from another. Together, the sub-networks extract features from the entire input signal. By forcing the network to solve cross-channel prediction tasks, we induce a representation within the network which transfers well to other, unseen tasks. This method achieves state-of-the-art performance on several large-scale transfer learning benchmarks.
UR - http://www.scopus.com/inward/record.url?scp=85044323260&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85044323260&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2017.76
DO - 10.1109/CVPR.2017.76
M3 - Conference contribution
AN - SCOPUS:85044323260
T3 - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
SP - 645
EP - 654
BT - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 21 July 2017 through 26 July 2017
ER -