TY  - CONF
AU  - Lu Yu
AU  - Vacit Oguz Yazici
AU  - Xialei Liu
AU  - Joost Van de Weijer
AU  - Yongmei Cheng
AU  - Arnau Ramisa
A2  - CVPR
PY  - 2019//
TI  - Learning Metrics from Teachers: Compact Networks for Image Embedding
BT  - 32nd IEEE Conference on Computer Vision and Pattern Recognition
SP  - 2907
EP  - 2916
N2  - Metric learning networks are used to compute image embeddings, which are widely used in many applications such as image retrieval and face recognition. In this paper, we propose to use network distillation to efficiently compute image embeddings with small networks. Network distillation has been successfully applied to improve image classification, but has hardly been explored for metric learning. To do so, we propose two new loss functions that model thecommunication of a deep teacher network to a small student network. We evaluate our system in several datasets, including CUB-200-2011, Cars-196, Stanford Online Products and show that embeddings computed using small student networks perform significantly better than those computed using standard networks of similar size. Results on a very compact network (MobileNet-0.25), which can beused on mobile devices, show that the proposed method can greatly improve Recall@1 results from 27.5% to 44.6%. Furthermore, we investigate various aspects of distillation for embeddings, including hint and attention layers, semisupervised learning and cross quality distillation.
UR  - https://ieeexplore.ieee.org/document/8953752
L1  - http://refbase.cvc.uab.es/files/YYL2019.pdf
UR  - http://dx.doi.org/10.1109/CVPR.2019.00302
N1  - LAMP; 600.109; 600.120
ID  - Lu Yu2019
ER  -