TY - JOUR
T1 - Discriminative Transfer Learning for Driving Pattern Recognition in Unlabeled Scenes
AU - Yang, Liu
AU - Li, Maoying
AU - Shen, Chenyang
AU - Hu, Qinghua
AU - Wen, Jia
AU - Xu, Shujie
N1 - Funding Information:
This work was supported in part by the National Natural Science Foundation of China under Grant 61732011 and Grant 61702358, in part by the Beijing Natural Science Foundation under Grant Z180006, in part by the Key Scientific and Technological Support Project of Tianjin Key Research and Development Program under Grant 18YFZCGX00390, and in part by the Tianjin Science and Technology Plan Project under Grant 19ZXZNGX00050.
Publisher Copyright:
© 2013 IEEE.
PY - 2022/3/1
Y1 - 2022/3/1
N2 - Driving pattern recognition based on features, such as GPS, gear, and speed information, is essential to develop intelligent transportation systems. However, it is usually expensive and labor intensive to collect a large amount of labeled driving data from real-world driving scenes. The lack of a labeled data problem in a driving scene substantially hinders the driving pattern recognition accuracy. To handle the scarcity of labeled data, we have developed a novel discriminative transfer learning method for driving pattern recognition to leverage knowledge from related scenes with labeled data to improve recognition performance in unlabeled scenes. Note that data from different scenes may have different distributions, which is a major bottleneck limiting the performance of transfer learning. To address this issue, the proposed method adopts a discriminative distribution matching scheme with the aid of pseudolabels in unlabeled scenes. It is able to reduce the intraclass distribution disagreement for the same driving pattern among labeled and unlabeled scenes while increasing the interclass distance among different patterns. Pseudolabels in unlabeled scenes are updated iteratively via an ensemble strategy that preserves the data structure while enhancing the model robustness. To evaluate the performance of the proposed method, we conducted comprehensive experiments on real-world parking lot datasets. The results show that the proposed method can substantially outperform state-of-the-art methods in driving pattern recognition.
AB - Driving pattern recognition based on features, such as GPS, gear, and speed information, is essential to develop intelligent transportation systems. However, it is usually expensive and labor intensive to collect a large amount of labeled driving data from real-world driving scenes. The lack of a labeled data problem in a driving scene substantially hinders the driving pattern recognition accuracy. To handle the scarcity of labeled data, we have developed a novel discriminative transfer learning method for driving pattern recognition to leverage knowledge from related scenes with labeled data to improve recognition performance in unlabeled scenes. Note that data from different scenes may have different distributions, which is a major bottleneck limiting the performance of transfer learning. To address this issue, the proposed method adopts a discriminative distribution matching scheme with the aid of pseudolabels in unlabeled scenes. It is able to reduce the intraclass distribution disagreement for the same driving pattern among labeled and unlabeled scenes while increasing the interclass distance among different patterns. Pseudolabels in unlabeled scenes are updated iteratively via an ensemble strategy that preserves the data structure while enhancing the model robustness. To evaluate the performance of the proposed method, we conducted comprehensive experiments on real-world parking lot datasets. The results show that the proposed method can substantially outperform state-of-the-art methods in driving pattern recognition.
KW - Driving pattern recognition
KW - interclass separability
KW - intraclass compactness
KW - maximum mean discrepancy (MMD)
KW - transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85126388832&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85126388832&partnerID=8YFLogxK
U2 - 10.1109/TCYB.2020.2987632
DO - 10.1109/TCYB.2020.2987632
M3 - Article
C2 - 32413940
AN - SCOPUS:85126388832
SN - 2168-2267
VL - 52
SP - 1429
EP - 1442
JO - IEEE Transactions on Cybernetics
JF - IEEE Transactions on Cybernetics
IS - 3
ER -