2000 character limit reached
Cooperative Students: Navigating Unsupervised Domain Adaptation in Nighttime Object Detection (2404.01988v3)
Published 2 Apr 2024 in cs.CV
Abstract: Unsupervised Domain Adaptation (UDA) has shown significant advancements in object detection under well-lit conditions; however, its performance degrades notably in low-visibility scenarios, especially at night, posing challenges not only for its adaptability in low signal-to-noise ratio (SNR) conditions but also for the reliability and efficiency of automated vehicles. To address this problem, we propose a \textbf{Co}operative \textbf{S}tudents (\textbf{CoS}) framework that innovatively employs global-local transformations (GLT) and a proxy-based target consistency (PTC) mechanism to capture the spatial consistency in day- and night-time scenarios effectively, and thus bridge the significant domain shift across contexts. Building upon this, we further devise an adaptive IoU-informed thresholding (AIT) module to gradually avoid overlooking potential true positives and enrich the latent information in the target domain. Comprehensive experiments show that CoS essentially enhanced UDA performance in low-visibility conditions and surpasses current state-of-the-art techniques, achieving an increase in mAP of 3.0\%, 1.9\%, and 2.5\% on BDD100K, SHIFT, and ACDC datasets, respectively. Code is available at https://github.com/jichengyuan/Cooperitive_Students.
- “Object detection in 20 years: A survey,” Proceedings of the IEEE, vol. 111, no. 3, pp. 257–276, 2023.
- “Crafting object detection in very low light,” in BMVC, 2021, vol. 1, p. 3.
- “Image-adaptive yolo for object detection in adverse weather conditions,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2022, vol. 36, pp. 1792–1800.
- “Bdd100k: A diverse driving dataset for heterogeneous multitask learning,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 2636–2645.
- “Domain adaptive faster r-cnn for object detection in the wild,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 3339–3348.
- “Boosting domain adaptation by discovering latent domains,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 3771–3780.
- “Visual domain adaptation with manifold embedded distribution alignment,” in Proceedings of the 26th ACM international conference on Multimedia, 2018, pp. 402–410.
- “Prior knowledge guided unsupervised domain adaptation,” in European Conference on Computer Vision. Springer, 2022, pp. 639–655.
- “Unsupervised domain adaptation for person re-identification with iterative soft clustering,” Knowledge-Based Systems, vol. 212, pp. 106644, 2021.
- “Unbiased mean teacher for cross-domain object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 4091–4101.
- “2pcnet: Two-phase consistency training for day-to-night unsupervised domain adaptive object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 11484–11493.
- “Consistent-teacher: Towards reducing inconsistent pseudo-targets in semi-supervised object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 3240–3249.
- “Dense learning based semi-supervised object detection,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 4815–4824.
- “Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results,” Advances in neural information processing systems, vol. 30, 2017.
- “Deep transfer learning with joint adaptation networks,” in International conference on machine learning. PMLR, 2017, pp. 2208–2217.
- “Adversarial discriminative domain adaptation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 7167–7176.
- “Cross-domain adaptive teacher for object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 7581–7590.
- “Fda: Fourier domain adaptation for semantic segmentation,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 4085–4095.
- “Forkgan: Seeing into the rainy night,” in Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part III 16. Springer, 2020, pp. 155–170.
- “Adversarial robustness for unsupervised domain adaptation,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2021, pp. 8568–8577.
- “Cdada: A curriculum domain adaptation for nighttime semantic segmentation,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 2962–2971.
- “Dannet: A one-stage domain adaptation network for unsupervised nighttime semantic segmentation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 15769–15778.
- “Unsupervised domain adaptation for nighttime aerial tracking,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 8896–8905.
- “Gan-based day-to-night image style transfer for nighttime vehicle detection,” IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 2, pp. 951–963, 2020.
- “Free lunch for domain adversarial training: Environment label smoothing,” in The Eleventh International Conference on Learning Representations, 2022.
- “Global and local contrast adaptive enhancement for non-uniform illumination color images,” in Proceedings of the IEEE International Conference on Computer Vision Workshops, 2017, pp. 3023–3030.
- “Unpaired image-to-image translation using cycle-consistent adversarial networks,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2223–2232.
- “Unsupervised image-to-image translation networks,” Advances in neural information processing systems, vol. 30, 2017.
- “Cross domain object detection by target-perceived dual branch distillation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 9570–9580.
- “Scale-aware domain adaptive faster r-cnn,” International Journal of Computer Vision, vol. 129, no. 7, pp. 2223–2243, 2021.
- “Shift: a synthetic driving dataset for continuous multi-task domain adaptation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 21371–21382.
- “Acdc: The adverse conditions dataset with correspondences for semantic driving scene understanding,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 10765–10775.
- “Faster r-cnn: Towards real-time object detection with region proposal networks,” Advances in neural information processing systems, vol. 28, 2015.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.