Deep learning technologies for shield tunneling: Challenges and opportunities
Shield tunneling has been prevalent in tunnel construction since its introduction into the
field. To take advantage of the massive data generated during tunneling and to assist in …
field. To take advantage of the massive data generated during tunneling and to assist in …
Class-wise Contrastive Prototype Learning for Semi-Supervised Classification under Intersectional Class Mismatch
Traditional Semi-Supervised Learning (SSL) classification methods focus on leveraging
unlabeled data to improve the model performance under the setting where labeled set and …
unlabeled data to improve the model performance under the setting where labeled set and …
Dynamic Weighted Adversarial Learning for Semi-Supervised Classification under Intersectional Class Mismatch
Nowadays, class-mismatch problem has drawn intensive attention in Semi-Supervised
Learning (SSL), where the classes of labeled data are assumed to be only a subset of the …
Learning (SSL), where the classes of labeled data are assumed to be only a subset of the …
Get a Head Start: Targeted Labeling at Source with Limited Annotation Overhead for Semi-Supervised Learning
H Zhu, Y Lu, Q Ma, X Zhou, F Xia… - … on Multimedia and …, 2023 - ieeexplore.ieee.org
Semi-supervised learning (SSL), which leverages limited labeled data and a large amount
of unlabeled data for model training, has been widely studied to mitigate the requirement for …
of unlabeled data for model training, has been widely studied to mitigate the requirement for …
Not All Classes are Equal: Adaptively Focus-Aware Confidence for Semi-Supervised Object Detection
H Zhu, Y Lu, H Zhao, G Zhao… - ICASSP 2023-2023 IEEE …, 2023 - ieeexplore.ieee.org
Semi-supervised object detection (SSOD) is a significant application of Semi-supervised
learning to further improve object detectors but suffers more seriously from confirmation bias …
learning to further improve object detectors but suffers more seriously from confirmation bias …