Metrics
4 Record Views
Conference proceeding
Improving Object Detection Robustness against Natural Perturbations through Synthetic Data Augmentation
CVIPPR '23: Proceedings of the 2023 Asia Conference on Computer Vision, Image Processing and Pattern Recognition, 7
ACM Other Conferences
CVIPPR 2023: 2023 Asia Conference on Computer Vision, Image Processing and Pattern Recognition (Phuket, Thailand, 04/28/2023–04/30/2023)
06/2023
Abstract
Robustness against real-world distribution shifts is crucial for the successful deployment of object detection models in practical applications. In this paper, we address the problem of assessing and enhancing the robustness of object detection models against natural perturbations, such as varying lighting conditions, blur, and brightness. We analyze four state-of-the-art deep neural network models, Detr-ResNet-101, Detr-ResNet-50, YOLOv4, and YOLOv4-tiny, using the COCO 2017 dataset and ExDark dataset. By simulating synthetic perturbations with the AugLy package, we systematically explore the optimal level of synthetic perturbation required to improve the models’ robustness through data augmentation techniques. Our comprehensive ablation study meticulously evaluates the impact of synthetic perturbations on object detection models’ performance against real-world distribution shifts, establishing a tangible connection between synthetic augmentation and real-world robustness. Our findings not only substantiate the effectiveness of synthetic perturbations in improving model robustness, but also provide valuable insights for researchers and practitioners in developing more robust and reliable object detection models tailored for real-world applications.
Related links
Details
- Title
- Improving Object Detection Robustness against Natural Perturbations through Synthetic Data Augmentation
- Publication Details
- CVIPPR '23: Proceedings of the 2023 Asia Conference on Computer Vision, Image Processing and Pattern Recognition, 7
- Resource Type
- Conference proceeding
- Conference
- CVIPPR 2023: 2023 Asia Conference on Computer Vision, Image Processing and Pattern Recognition (Phuket, Thailand, 04/28/2023–04/30/2023)
- Publisher
- Association for Computing Machinery (ACM); New York, NY, United States
- Series
- ACM Other Conferences
- Number of pages
- 6
- Copyright
- © 2023 ACM.
- Identifiers
- 99381512425606600
- Academic Unit
- Intelligent Systems and Robotics; Hal Marcus College of Science and Engineering
- Language
- English