Semantic Segmentation With Unsupervised Domain Adaptation Under Varying Weather Conditions for Autonomous Vehicles

Erkent, Özgür; Laugier, Christian

doi:10.1109/lra.2020.2978666

Cited by 30 publications

(11 citation statements)

References 30 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…156 semantic segmentation

self-supervised A, B, C, F 2020 Erkent et al. 157 semantic segmentation

Unsupervised A, F 2014 Eigen et al. 14 depth estimation Supervised F 2015 Eigen et al.…”

Section: Main Textmentioning

confidence: 99%

“…This segmentation adaptation model was trained on both synthetic and real-world datasets, which improved the segmentation performance of real-world data. In addition, Erkent and Laugier 157 considered a method of semantic segmentation adapted to different weather conditions, which can achieve satisfactory accuracy for semantic segmentation without the need of labeling the weather conditions of the source or target domain.…”

Section: Main Textmentioning

confidence: 99%

See 1 more Smart Citation

When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey

et al. 2020

View full text Add to dashboard Cite

With widespread applications of artificial intelligence (AI), the capabilities of the perception, understanding, decision-making, and control for autonomous systems have improved significantly in recent years. When autonomous systems consider the performance of accuracy and transferability, several AI methods, such as adversarial learning, reinforcement learning (RL), and meta-learning, show their powerful performance. Here, we review the learning-based approaches in autonomous systems from the perspectives of accuracy and transferability. Accuracy means that a well-trained model shows good results during the testing phase, in which the testing set shares a same task or a data distribution with the training set. Transferability means that when a well-trained model is transferred to other testing domains, the accuracy is still good. Firstly, we introduce some basic concepts of transfer learning and then present some preliminaries of adversarial learning, RL, and meta-learning. Secondly, we focus on reviewing the accuracy or transferability or both of these approaches to show the advantages of adversarial learning, such as generative adversarial networks, in typical computer vision tasks in autonomous systems, including image style transfer, image super-resolution, image deblurring/dehazing/rain removal, semantic segmentation, depth estimation, pedestrian detection, and person re-identification. We furthermore review the performance of RL and meta-learning from the aspects of accuracy or transferability or both of them in autonomous systems, involving pedestrian tracking, robot navigation, and robotic manipulation. Finally, we discuss several challenges and future topics for the use of adversarial learning, RL, and meta-learning in autonomous systems.

show abstract

“…156 semantic segmentation

self-supervised A, B, C, F 2020 Erkent et al. 157 semantic segmentation

Unsupervised A, F 2014 Eigen et al. 14 depth estimation Supervised F 2015 Eigen et al.…”

Section: Main Textmentioning

confidence: 99%

Section: Main Textmentioning

confidence: 99%

When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Zhang et al [29] use it for instance segmentation from synthetic to real domain . Adaptation approaches do not always use GANs, for example Peng et al [30] implement Wasserstein GANs (W-GANs) [31], Erkent et al [7] use W-GANs and MMDs for adaptation of semantic segmentation.…”

Section: B Unsupervised Domain Adaptationmentioning

confidence: 99%

“…1. More details and variants of the algorithm can be found in [7] with further experiments for the semantic segmentation problem.…”

Section: Domain Adaptation For Instance Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Instance Segmentation with Unsupervised Adaptation to Different Domains for Autonomous Vehicles

Diaz-Zapata

Erkent

Laugier

2020

2020 16th International Conference on Control, Automation, Robotics and Vision (ICARCV)

Self Cite

View full text Add to dashboard Cite

Detection of the objects around a vehicle is important for a safe and successful navigation of an autonomous vehicle. Instance segmentation provides a fine and accurate classification of the objects such as cars, trucks, pedestrians, etc. In this study, we propose a fast and accurate approach which can detect and segment the object instances which can be adapted to new conditions without requiring the labels from the new condition. Furthermore, the performance of the instance segmentation does not degrade in detection of the objects in the original condition after it adapts to the new condition. To our knowledge, currently there are not other methods which perform unsupervised domain adaptation for the task of instance segmentation using non-synthetic datasets. We evaluate the adaptation capability of our method on two datasets. Firstly, we test its capacity of adapting to a new domain; secondly, we test its ability to adapt to new weather conditions. The results show that it can adapt to new conditions with an improved accuracy while preserving the accuracy of the original condition.

show abstract

GridTrack: Detection and Tracking of Multiple Objects in Dynamic Occupancy Grids

Erkent

González

Paigwar

et al. 2021

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Multiple Object Tracking is an important task for autonomous vehicles. However, it gets difficult to track objects when it is hard to detect them due to occlusion or distance to the sensors. We propose a method, "GridTrack", to overcome this difficulty. We fuse a dynamic occupancy grid map (DOGMa) with an object detector. DOGMa is obtained by applying a Bayesian filter on raw sensor data. This improves the tracking of the partially observed / unobserved objects with the help of the Bayesian filter on raw data, which has a powerful prediction capability. We develop a network to track the objects on the grid and fuse information from previous detections in this network. The experiments show that the multi-object tracking accuracy is high with the usage of the proposed method.

show abstract

Semantic Segmentation With Unsupervised Domain Adaptation Under Varying Weather Conditions for Autonomous Vehicles

Cited by 30 publications

References 30 publications

When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey

When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey

Instance Segmentation with Unsupervised Adaptation to Different Domains for Autonomous Vehicles

GridTrack: Detection and Tracking of Multiple Objects in Dynamic Occupancy Grids

Contact Info

Product

Resources

About