StRDAN: Synthetic-to-Real Domain Adaptation Network for Vehicle Re-Identification

04/25/2020

∙

Vehicle re-identification aims to obtain the same vehicles from vehicle images. It is challenging but essential for analyzing and predicting traffic flow in the city. Although deep learning methods have achieved enormous progress in this task, requiring a large amount of data is a critical shortcoming. To tackle this problem, we propose a novel framework called Synthetic-to-Real Domain Adaptation Network (StRDAN), which is trained with inexpensive large-scale synthetic data as well as real data to improve performance. The training method for StRDAN is combined with domain adaptation and semi-supervised learning methods and their associated losses. StRDAN shows a significant improvement over the baseline model, which is trained using only real data, in two main datasets: VeRi and CityFlow-ReID. Evaluating with the mean average precision (mAP) metric, our model outperforms the reference model by 12.87

READ FULL TEXT

StRDAN: Synthetic-to-Real Domain Adaptation Network for Vehicle Re-Identification

Large-scale ASR Domain Adaptation using Self- and Semi-supervised Learning

Semi-supervised Large-scale Fiber Detection in Material Images with Synthetic Data

Content Disentanglement for Semantically Consistent Synthetic-to-RealDomain Adaptation in Urban Traffic Scenes

MLReal: Bridging the gap between training on synthetic data and real data applications in machine learning

A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation

Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances

Employing Real Training Data for Deep Noise Suppression

StRDAN: Synthetic-to-Real Domain Adaptation Network for Vehicle Re-Identification

Related Research

Large-scale ASR Domain Adaptation using Self- and Semi-supervised Learning

Semi-supervised Large-scale Fiber Detection in Material Images with Synthetic Data

Content Disentanglement for Semantically Consistent Synthetic-to-RealDomain Adaptation in Urban Traffic Scenes

MLReal: Bridging the gap between training on synthetic data and real data applications in machine learning

A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation

Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances

Employing Real Training Data for Deep Noise Suppression