StRDAN: Synthetic-to-Real Domain Adaptation Network for Vehicle
Re-Identification
- URL: http://arxiv.org/abs/2004.12032v2
- Date: Fri, 17 Jul 2020 07:44:10 GMT
- Title: StRDAN: Synthetic-to-Real Domain Adaptation Network for Vehicle
Re-Identification
- Authors: Sangrok Lee, Eunsoo Park, Hongsuk Yi, Sang Hun Lee
- Abstract summary: Vehicle re-identification aims to obtain the same vehicles from vehicle images.
This is challenging but essential for analyzing and predicting traffic flow in the city.
We propose a synthetic-to-real domain adaptation network (StRDAN) framework, which can be trained with inexpensive large-scale synthetic and real data to improve performance.
- Score: 16.14221315208939
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Vehicle re-identification aims to obtain the same vehicles from vehicle
images. This is challenging but essential for analyzing and predicting traffic
flow in the city. Although deep learning methods have achieved enormous
progress for this task, their large data requirement is a critical shortcoming.
Therefore, we propose a synthetic-to-real domain adaptation network (StRDAN)
framework, which can be trained with inexpensive large-scale synthetic and real
data to improve performance. The StRDAN training method combines domain
adaptation and semi-supervised learning methods and their associated losses.
StRDAN offers significant improvement over the baseline model, which can only
be trained using real data, for VeRi and CityFlow-ReID datasets, achieving 3.1%
and 12.9% improved mean average precision, respectively.
Related papers
- Enhancing Traffic Sign Recognition with Tailored Data Augmentation: Addressing Class Imbalance and Instance Scarcity [0.0]
This paper tackles critical challenges in traffic sign recognition (TSR), which is essential for road safety.
We introduce tailored data augmentation techniques, including synthetic image generation and geometric transformations.
Our methodology incorporates diverse augmentation processes to accurately simulate real-world conditions, thereby expanding the training data's variety and representativeness.
arXiv Detail & Related papers (2024-06-05T18:45:45Z) - A Fully Data-Driven Approach for Realistic Traffic Signal Control Using
Offline Reinforcement Learning [18.2541182874636]
We propose a fully Data-Driven and simulator-free framework for realistic Traffic Signal Control (D2TSC)
We combine well-established traffic flow theory with machine learning to infer the reward signals from coarse-grained traffic data.
Our approach achieves superior performance over conventional and offline RL baselines, and also enjoys much better real-world applicability.
arXiv Detail & Related papers (2023-11-27T15:29:21Z) - Reinforcement Learning with Human Feedback for Realistic Traffic
Simulation [53.85002640149283]
Key element of effective simulation is the incorporation of realistic traffic models that align with human knowledge.
This study identifies two main challenges: capturing the nuances of human preferences on realism and the unification of diverse traffic simulation models.
arXiv Detail & Related papers (2023-09-01T19:29:53Z) - One-Shot Domain Adaptive and Generalizable Semantic Segmentation with
Class-Aware Cross-Domain Transformers [96.51828911883456]
Unsupervised sim-to-real domain adaptation (UDA) for semantic segmentation aims to improve the real-world test performance of a model trained on simulated data.
Traditional UDA often assumes that there are abundant unlabeled real-world data samples available during training for the adaptation.
We explore the one-shot unsupervised sim-to-real domain adaptation (OSUDA) and generalization problem, where only one real-world data sample is available.
arXiv Detail & Related papers (2022-12-14T15:54:15Z) - Self-Supervised Pre-Training for Transformer-Based Person
Re-Identification [54.55281692768765]
Transformer-based supervised pre-training achieves great performance in person re-identification (ReID)
Due to the domain gap between ImageNet and ReID datasets, it usually needs a larger pre-training dataset to boost the performance.
This work aims to mitigate the gap between the pre-training and ReID datasets from the perspective of data and model structure.
arXiv Detail & Related papers (2021-11-23T18:59:08Z) - Large-scale ASR Domain Adaptation using Self- and Semi-supervised
Learning [26.110250680951854]
We utilize the combination of self- and semi-supervised learning methods to solve unseen domain adaptation problem in a large-scale production setting for online ASR model.
This approach demonstrates that using the source domain data with a small fraction of the target domain data (3%) can recover the performance gap compared to a full data baseline.
arXiv Detail & Related papers (2021-10-01T01:48:33Z) - Transformer Networks for Data Augmentation of Human Physical Activity
Recognition [61.303828551910634]
State of the art models like Recurrent Generative Adrial Networks (RGAN) are used to generate realistic synthetic data.
In this paper, transformer based generative adversarial networks which have global attention on data, are compared on PAMAP2 and Real World Human Activity Recognition data sets with RGAN.
arXiv Detail & Related papers (2021-09-02T16:47:29Z) - Attention-based Adversarial Appearance Learning of Augmented Pedestrians [49.25430012369125]
We propose a method to synthesize realistic data for the pedestrian recognition task.
Our approach utilizes an attention mechanism driven by an adversarial loss to learn domain discrepancies.
Our experiments confirm that the proposed adaptation method is robust to such discrepancies and reveals both visual realism and semantic consistency.
arXiv Detail & Related papers (2021-07-06T15:27:00Z) - Physics-Informed Deep Learning for Traffic State Estimation [3.779860024918729]
Traffic state estimation (TSE) reconstructs the traffic variables (e.g., density) on road segments using partially observed data.
This paper introduces a physics-informed deep learning (PIDL) framework to efficiently conduct high-quality TSE with small amounts of observed data.
arXiv Detail & Related papers (2021-01-17T03:28:32Z) - Deep Traffic Sign Detection and Recognition Without Target Domain Real
Images [52.079665469286496]
We propose a novel database generation method that requires no real image from the target-domain, and (ii) templates of the traffic signs.
The method does not aim at overcoming the training with real data, but to be a compatible alternative when the real data is not available.
On large data sets, training with a fully synthetic data set almost matches the performance of training with a real one.
arXiv Detail & Related papers (2020-07-30T21:06:47Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.