Recursive noisy label learning paradigm based on confidence measurement for semi-supervised depth completion

• Published in: International journal of machine learning and cybernetics Vol. 15; no. 8; pp. 3201 - 3219
• Main Authors: Chen, Guancheng, Qin, Huabiao, Huang, Linyi
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01-08-2024; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Complex Systems; Computational Intelligence; Continuous improvement; Control; Engineering; Image reconstruction; Labels; Lidar; Mechatronics; Neural networks; Object recognition; Original Article; Pattern Recognition; Robotics; Semi-supervised learning; Supervision; Systems Biology; Confidence measurement; Semi-supervised learning; Depth completion; Noisy label learning; Multimodal learning
• ISSN: 1868-8071; 1868-808X
• DOI: 10.1007/s13042-023-02088-x

Depth completion is a critical task for extensive applications such as 3D reconstruction and object detection. Recent semi-supervised depth completion techniques based on Stereo-LiDAR fusion has gradually attracted attention due to its ability to realize semi-supervised training under the weakly supervised constraints provided by the sparse LiDAR points as well as the view synthesis consistency provided by the stereo images. However, among these methods, noisy label as a conventional supervised signal for semi-supervised learning have not been taken seriously. To this end, we first propose a semi-supervised learning framework called
Recursive Noise Label Learning
(RNLL), which is able to maximize the potential of noisy label learning by establishing a recursive noisy label optimization and model learning mechanism. Second, based on the proposed RNLL framework, we come up with a novel semi-supervised depth completion model, UAMD-Net-RNLL, which integrates the CCNN model to accomplish the confidence measure of depth prediction on the basis of the original UAMD-Net model, and realizes the noise filtering of the noisy depth maps and adaptive loss computation by constructing the confidence-guided noisy label loss function. Finally, for the noisy label and photometric consistency loss constraints in multiple rounds of training, we utilize dynamic loss weights to describe their importance changes, and realize the continuous improvement of the prediction performance of the semi-supervised depth completion model. Extensive experimental results conducted on KITTI and DrivingStereo depth completion datasets prove that our technique achieves large performance gain, clearly outperforming competing methods and setting a new state-of-the-art for semi-supervised depth completion.