Multi-scale Vehicle Re-identification Using Self-adapting Label Smoothing Regularization
Yue Xu, Na Jiang, Lei Zhang, Zhong Zhou, Wei Wu
Abstract
Vehicle re-identification (re-id) plays an important role in intelligent surveillance. Since difference vehicle models may have similar appearances, together with the problem of image scale variations, the vehicle re-id remains long-term challenging. We present a novel multi-scale vehicle re-id framework using self-adapting label smoothing regularization (SLSR). It integrates the appearance information from multi-scale images to alleviate the influence of scale changes caused by perspectives. To enhance the generalization ability in feature representations, we design the self-adapting label smoothing regulation in semi-supervised training process. It dynamically assigns labels to fake images to realize data augmentation. We validate the effectiveness of our proposed framework on popular VeRi and VehicleID datasets. Extensive experimental results demonstrate that our method outperforms most state-of-the-art methods on both datasets. Especially, we exceeds the latest method by 3.81% in mAP and 5.32% in rank-1 on VeRi dataset.
BibTeX
@inproceedings{icassp2019_multiscalevehicl,
title = {Multi-scale Vehicle Re-identification Using Self-adapting Label Smoothing Regularization},
author = {Yue Xu and Na Jiang and Lei Zhang and Zhong Zhou and Wei Wu},
booktitle = {ICASSP 2019},
year = {2019}
}