Abstract
Current state-of-the-art classification and detection algorithms train deep convolutional networks using labeled data. In this work we study unsupervised feature learning with convolutional networks in the context of temporally coherent unlabeled data. We focus on feature learning from unlabeled video data, using the assumption that adjacent video frames contain semantically similar information. This assumption is exploited to train a convolutional pooling auto-encoder regularized by slowness and sparsity priors. We establish a connection between slow feature learning and metric learning. Using this connection we define "temporal coherence" - a criterion which can be used to set hyper-parameters in a principled and automated manner. In a transfer learning experiment, we show that the resulting encoder can be used to define a more semantically coherent metric without the use of labels.
Original language | English (US) |
---|---|
Title of host publication | Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 4086-4093 |
Number of pages | 8 |
Volume | 11-18-December-2015 |
ISBN (Electronic) | 9781467383912 |
DOIs | |
State | Published - Feb 17 2016 |
Event | 15th IEEE International Conference on Computer Vision, ICCV 2015 - Santiago, Chile Duration: Dec 11 2015 → Dec 18 2015 |
Other
Other | 15th IEEE International Conference on Computer Vision, ICCV 2015 |
---|---|
Country | Chile |
City | Santiago |
Period | 12/11/15 → 12/18/15 |
Fingerprint
ASJC Scopus subject areas
- Software
- Computer Vision and Pattern Recognition
Cite this
Unsupervised learning of spatiotemporally coherent metrics. / Goroshin, Ross; Bruna Estrach, Joan; Tompson, Jonathan; Eigen, David; LeCun, Yann.
Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015. Vol. 11-18-December-2015 Institute of Electrical and Electronics Engineers Inc., 2016. p. 4086-4093 7410822.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Unsupervised learning of spatiotemporally coherent metrics
AU - Goroshin, Ross
AU - Bruna Estrach, Joan
AU - Tompson, Jonathan
AU - Eigen, David
AU - LeCun, Yann
PY - 2016/2/17
Y1 - 2016/2/17
N2 - Current state-of-the-art classification and detection algorithms train deep convolutional networks using labeled data. In this work we study unsupervised feature learning with convolutional networks in the context of temporally coherent unlabeled data. We focus on feature learning from unlabeled video data, using the assumption that adjacent video frames contain semantically similar information. This assumption is exploited to train a convolutional pooling auto-encoder regularized by slowness and sparsity priors. We establish a connection between slow feature learning and metric learning. Using this connection we define "temporal coherence" - a criterion which can be used to set hyper-parameters in a principled and automated manner. In a transfer learning experiment, we show that the resulting encoder can be used to define a more semantically coherent metric without the use of labels.
AB - Current state-of-the-art classification and detection algorithms train deep convolutional networks using labeled data. In this work we study unsupervised feature learning with convolutional networks in the context of temporally coherent unlabeled data. We focus on feature learning from unlabeled video data, using the assumption that adjacent video frames contain semantically similar information. This assumption is exploited to train a convolutional pooling auto-encoder regularized by slowness and sparsity priors. We establish a connection between slow feature learning and metric learning. Using this connection we define "temporal coherence" - a criterion which can be used to set hyper-parameters in a principled and automated manner. In a transfer learning experiment, we show that the resulting encoder can be used to define a more semantically coherent metric without the use of labels.
UR - http://www.scopus.com/inward/record.url?scp=84973902378&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84973902378&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2015.465
DO - 10.1109/ICCV.2015.465
M3 - Conference contribution
AN - SCOPUS:84973902378
VL - 11-18-December-2015
SP - 4086
EP - 4093
BT - Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015
PB - Institute of Electrical and Electronics Engineers Inc.
ER -