Search Results for author: Wenxuan Ma

Found 7 papers, 6 papers with code

Language Semantic Graph Guided Data-Efficient Learning

1 code implementation NeurIPS 2023 Wenxuan Ma, Shuang Li, Lincan Cai, Jingxuan Kang

Therefore, to achieve data-efficient learning, researchers typically explore approaches that can leverage more related or unlabeled data without necessitating additional manual labeling efforts, such as Semi-Supervised Learning (SSL), Transfer Learning (TL), and Data Augmentation (DA).

Data Augmentation Transfer Learning

Improving Uncertainty Quantification of Variance Networks by Tree-Structured Learning

1 code implementation24 Dec 2022 Wenxuan Ma, Xing Yan, Kun Zhang

A tree is built upon giving the training data, whose leaf nodes represent different regions where region-specific neural networks are trained to predict both the mean and the variance for quantifying uncertainty.

Uncertainty Quantification

Ensemble Multi-Quantiles: Adaptively Flexible Distribution Prediction for Uncertainty Quantification

1 code implementation26 Nov 2022 Xing Yan, Yonghua Su, Wenxuan Ma

We seek an adaptive balance between the structural integrity and the flexibility for $\mathbb{P}(\mathbf{y}|\mathbf{X}=x)$, while Gaussian assumption results in a lack of flexibility for real data and highly flexible approaches (e. g., estimating the quantiles separately without a distribution structure) inevitably have drawbacks and may not lead to good generalization.

Additive models regression +1

Making the Best of Both Worlds: A Domain-Oriented Transformer for Unsupervised Domain Adaptation

1 code implementation2 Aug 2022 Wenxuan Ma, Jinming Zhang, Shuang Li, Chi Harold Liu, Yulin Wang, Wei Li

To alleviate these issues, we propose to simultaneously conduct feature alignment in two individual spaces focusing on different domains, and create for each space a domain-oriented classifier tailored specifically for that domain.

Pseudo Label Unsupervised Domain Adaptation

Dynamic Domain Adaptation for Efficient Inference

1 code implementation CVPR 2021 Shuang Li, Jinming Zhang, Wenxuan Ma, Chi Harold Liu, Wei Li

Domain adaptation (DA) enables knowledge transfer from a labeled source domain to an unlabeled target domain by reducing the cross-domain distribution discrepancy.

Domain Generalization Transfer Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.