Towards discriminability and diversity: Batch nuclear-norm maximization under label insufficient situations

S Cui, S Wang, J Zhuo, L Li… - Proceedings of the …, 2020 - openaccess.thecvf.com
The learning of the deep networks largely relies on the data with human-annotated labels. In
some label insufficient situations, the performance degrades on the decision boundary with …

Cross-domain adaptive clustering for semi-supervised domain adaptation

J Li, G Li, Y Shi, Y Yu - … of the IEEE/CVF conference on …, 2021 - openaccess.thecvf.com
In semi-supervised domain adaptation, a few labeled samples per class in the target domain
guide features of the remaining target samples to aggregate around them. However, the …

Ml-lmcl: Mutual learning and large-margin contrastive learning for improving asr robustness in spoken language understanding

X Cheng, B Cao, Q Ye, Z Zhu, H Li, Y Zou - arXiv preprint arXiv …, 2023 - arxiv.org
Spoken language understanding (SLU) is a fundamental task in the task-oriented dialogue
systems. However, the inevitable errors from automatic speech recognition (ASR) usually …

Mcf: Mutual correction framework for semi-supervised medical image segmentation

Y Wang, B Xiao, X Bi, W Li… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Semi-supervised learning is a promising method for medical image segmentation under
limited annotation. However, the model cognitive bias impairs the segmentation …

Alignsam: Aligning segment anything model to open context via reinforcement learning

D Huang, X Xiong, J Ma, J Li, Z Jie… - Proceedings of the …, 2024 - openaccess.thecvf.com
Powered by massive curated training data Segment Anything Model (SAM) has
demonstrated its impressive generalization capabilities in open-world scenarios with the …

Towards cross-modality medical image segmentation with online mutual knowledge distillation

K Li, L Yu, S Wang, PA Heng - Proceedings of the AAAI conference on …, 2020 - ojs.aaai.org
The success of deep convolutional neural networks is partially attributed to the massive
amount of annotated training data. However, in practice, medical data annotations are …

Adaptive betweenness clustering for semi-supervised domain adaptation

J Li, G Li, Y Yu - IEEE Transactions on Image Processing, 2023 - ieeexplore.ieee.org
Compared to unsupervised domain adaptation, semi-supervised domain adaptation (SSDA)
aims to significantly improve the classification performance and generalization capability of …

Inter-domain mixup for semi-supervised domain adaptation

J Li, G Li, Y Yu - Pattern Recognition, 2024 - Elsevier
Semi-supervised domain adaptation (SSDA) aims to bridge source and target domain
distributions, with a small number of target labels available, achieving better classification …

Self-ensembling co-training framework for semi-supervised COVID-19 CT segmentation

C Li, L Dong, Q Dou, F Lin, K Zhang… - IEEE Journal of …, 2021 - ieeexplore.ieee.org
The coronavirus disease 2019 (COVID-19) has become a severe worldwide health
emergency and is spreading at a rapid rate. Segmentation of COVID lesions from computed …

Semi-supervised learning with pseudo-negative labels for image classification

H Xu, H Xiao, H Hao, L Dong, X Qiu, C Peng - Knowledge-Based Systems, 2023 - Elsevier
Semi-supervised learning frameworks usually adopt mutual learning approaches with
multiple submodels to learn from different perspectives. Usually, a high threshold is used to …