TY - GEN
T1 - A Shortly and Densely Connected Convolutional Neural Network for Vehicle Re-identification
AU - Zhu, Jianqing
AU - Zeng, Huanqiang
AU - Lei, Zhen
AU - Liao, Shengcai
AU - Zheng, Lixin
AU - Cai, Canhui
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/11/26
Y1 - 2018/11/26
N2 - In this paper, we propose a shortly and densely connected convolutional neural network (SDC-CNN) for vehicle re-identification. The proposed SDC-CNN mainly consists of short and dense units (SDUs), necessary pooling and normalization layers. The main contribution lies at the design of short and dense connection mechanism, which would effectively improve the feature learning ability. Specifically, in the proposed short and dense connection mechanism, each SDU contains a short list of densely connected convolutional layers and each convolutional layer is of the same appropriate channels. Consequently, the number of connections and the input channel of each convolutional layer are limited in each SDU, and the architecture of SDC-CNN is simple. Extensive experiments on both VeRi and VehicleID datasets show that the proposed SDC-CNN is obviously superior to multiple state-of-the-art vehicle re-identification methods.
AB - In this paper, we propose a shortly and densely connected convolutional neural network (SDC-CNN) for vehicle re-identification. The proposed SDC-CNN mainly consists of short and dense units (SDUs), necessary pooling and normalization layers. The main contribution lies at the design of short and dense connection mechanism, which would effectively improve the feature learning ability. Specifically, in the proposed short and dense connection mechanism, each SDU contains a short list of densely connected convolutional layers and each convolutional layer is of the same appropriate channels. Consequently, the number of connections and the input channel of each convolutional layer are limited in each SDU, and the architecture of SDC-CNN is simple. Extensive experiments on both VeRi and VehicleID datasets show that the proposed SDC-CNN is obviously superior to multiple state-of-the-art vehicle re-identification methods.
UR - http://www.scopus.com/inward/record.url?scp=85059740913&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85059740913&partnerID=8YFLogxK
U2 - 10.1109/ICPR.2018.8545514
DO - 10.1109/ICPR.2018.8545514
M3 - Conference contribution
AN - SCOPUS:85059740913
T3 - Proceedings - International Conference on Pattern Recognition
SP - 3285
EP - 3290
BT - 2018 24th International Conference on Pattern Recognition, ICPR 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 24th International Conference on Pattern Recognition, ICPR 2018
Y2 - 20 August 2018 through 24 August 2018
ER -