2000 character limit reached
Lifelong Change Detection: Continuous Domain Adaptation for Small Object Change Detection in Every Robot Navigation (2306.16086v1)
Published 28 Jun 2023 in cs.CV
Abstract: The recently emerging research area in robotics, ground view change detection, suffers from its ill-posed-ness because of visual uncertainty combined with complex nonlinear perspective projection. To regularize the ill-posed-ness, the commonly applied supervised learning methods (e.g., CSCD-Net) rely on manually annotated high-quality object-class-specific priors. In this work, we consider general application domains where no manual annotation is available and present a fully self-supervised approach. The present approach adopts the powerful and versatile idea that object changes detected during everyday robot navigation can be reused as additional priors to improve future change detection tasks. Furthermore, a robustified framework is implemented and verified experimentally in a new challenging practical application scenario: ground-view small object change detection.
- Dr-tanet: Dynamic receptive temporal attention network for street scene change detection. In 2021 IEEE Intelligent Vehicles Symposium (IV), pages 502–509. IEEE, 2021.
- Weakly supervised silhouette-based semantic scene change detection. In 2020 IEEE International conference on robotics and automation (ICRA), pages 6861–6867. IEEE, 2020.
- Microsoft coco: Common objects in context, 2014.
- Fast change detection for camera-based surveillance systems. In 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), pages 2481–2486, 2016.
- Land cover change detection with vhr satellite imagery based on multi-scale slic-cnn and scae features. IEEE Access, 8:228070–228087, 2020.
- Fully convolutional networks for multisource building extraction from an open aerial and satellite imagery data set. IEEE Transactions on Geoscience and Remote Sensing, 57(1):574–586, 2019.
- Landslide inventory mapping from bitemporal images using deep convolutional neural networks. IEEE Geoscience and Remote Sensing Letters, 16(6):982–986, 2019.
- CREST JST. Change detection from a street image pair using cnn features and superpixel segmentation. 2015.
- Dense optical flow based change detection network robust to difference of camera viewpoints. arXiv preprint arXiv:1712.02941, 2017.
- Flownet: Learning optical flow with convolutional networks. In Proceedings of the IEEE international conference on computer vision, pages 2758–2766, 2015.
- Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee, 2009.
- Self-training: A survey. arXiv preprint arXiv:2202.12040, 2022.
- Asymmetric tri-training for unsupervised domain adaptation. In International Conference on Machine Learning, pages 2988–2997. PMLR, 2017.
- Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In Proceedings of the European conference on computer vision (ECCV), pages 289–305, 2018.
- Confidence regularized self-training. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 5982–5991, 2019.
- Continuous manifold based adaptation for evolving visual domains. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 867–874, 2014.
- Incremental adversarial domain adaptation for continually changing environments. In 2018 IEEE International conference on robotics and automation (ICRA), pages 4489–4495. IEEE, 2018.
- Continual adaptation of visual representations via domain randomization and meta-learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4443–4453, 2021.
- Adapting to continuously shifting domains. 2018.
- Learning spatial regularization with image-level supervisions for multi-label image classification. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5513–5522, 2017.
- Deep co-occurrence feature learning for visual object recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4123–4132, 2017.
- Harmonizing transferability and discriminability for adapting object detectors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8869–8878, 2020.
- Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
- Learning accurate dense correspondences and when to trust them. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5714–5724, 2021.