TY - GEN
T1 - Few-Shot Hash Learning for Image Retrieval
AU - Gui, Liangke
AU - Wang, Yu Xiong
AU - Hebert, Martial
N1 - Funding Information:
Acknowledgments: This work was supported in part by ONR MURI N000141612007 and U.S. Army Research Laboratory (ARL) under the Collaborative Technology Alliance Program, Cooperative Agreement W911NF-10-2-0016. We also thank NVIDIA for donating GPUs and AWS Cloud Credits for Research program.
Funding Information:
This work was supported in part by ONR MURI N000141612007 and U.S. Army Research Laboratory (ARL) under the Collaborative Technology Alliance Program, Cooperative Agreement W911NF-10-2-0016. We also thank NVIDIA for donating GPUs and AWS Cloud Credits for Research program.
Publisher Copyright:
© 2017 IEEE.
PY - 2017/7/1
Y1 - 2017/7/1
N2 - Current approaches to hash based semantic image retrieval assume a set of pre-defined categories and rely on supervised learning from a large number of annotated samples. The need for labeled samples limits their applicability in scenarios in which a user provides at query time a small set of training images defining a customized novel category. This paper addresses the problem of few-shot hash learning, in the spirit of one-shot learning in image recognition and classification and early work on locality sensitive hashing. More precisely, our approach is based on the insight that universal hash functions can be learned off-line from unlabeled data because of the information implicit in the density structure of a discriminative feature space. We can then select a task-specific combination of hash codes for a novel category from a few labeled samples. The resulting unsupervised generic hashing (UGH) significantly outperforms current supervised and unsupervised hashing approaches on image retrieval tasks with small training samples.
AB - Current approaches to hash based semantic image retrieval assume a set of pre-defined categories and rely on supervised learning from a large number of annotated samples. The need for labeled samples limits their applicability in scenarios in which a user provides at query time a small set of training images defining a customized novel category. This paper addresses the problem of few-shot hash learning, in the spirit of one-shot learning in image recognition and classification and early work on locality sensitive hashing. More precisely, our approach is based on the insight that universal hash functions can be learned off-line from unlabeled data because of the information implicit in the density structure of a discriminative feature space. We can then select a task-specific combination of hash codes for a novel category from a few labeled samples. The resulting unsupervised generic hashing (UGH) significantly outperforms current supervised and unsupervised hashing approaches on image retrieval tasks with small training samples.
UR - http://www.scopus.com/inward/record.url?scp=85046259982&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85046259982&partnerID=8YFLogxK
U2 - 10.1109/ICCVW.2017.148
DO - 10.1109/ICCVW.2017.148
M3 - Conference contribution
AN - SCOPUS:85046259982
T3 - Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
SP - 1228
EP - 1237
BT - Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017
Y2 - 22 October 2017 through 29 October 2017
ER -