XZXiaomin Zhang

Xiaomin Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Xiaomin Zhang has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    BAE-ViT: An Efficient Multimodal Vision Transformer for Bone Age Estimation

    by Jinnian Zhang, Weijie Chen, Tanmayee Joshi, Xiaomin Zhang, Po-Ling Loh, Varun Jog, Richard J. Bruce, John W. Garrett, Alan B. McMillan

    This research introduces BAE-ViT, a specialized vision transformer model developed for bone age estimation (BAE). This model is designed to efficiently merge image and sex data, a capability not present in traditional convolutional neural networks (CNNs). BAE-ViT employs a novel data fusion method to facilitate detailed interactions between visual and non-visual data by tokenizing non-visual information and concatenating all tokens (visual or non-visual) as the input to the model. The model underwent training on a large-scale dataset from the 2017 RSNA Pediatric Bone Age Machine Learning Challenge, where it exhibited commendable performance, particularly excelling in handling image distortions compared to existing models. The effectiveness of BAE-ViT was further affirmed through statistical analysis, demonstrating a strong correlation with the actual ground-truth labels. This study contributes to the field by showcasing the potential of vision transformers as a viable option for integrating multimodal data in medical imaging applications, specifically emphasizing their capacity to incorporate non-visual elements like sex information into the framework. This tokenization method not only demonstrates superior performance in this specific task but also offers a versatile framework for integrating multimodal data in medical imaging applications.


  • Open Access

    On the identifiability of mixtures of ranking models

    by Xiaomin Zhang, Xucheng Zhang, Po-Ling Loh, Yingyu Liang

    Mixtures of ranking models are standard tools for ranking problems. However, even the fundamental question of parameter identifiability is not fully understood: the identifiability of a mixture model with two Bradley-Terry-Luce (BTL) components has remained open. In this work, we show that popular mixtures of ranking models with two components (BTL, multinomial logistic models with slates of size 3, or Plackett-Luce) are generically identifiable, i.e., the ground-truth parameters can be identified except when they are from a pathological subset of measure zero. We provide a framework for verifying the number of solutions in a general family of polynomial systems using algebraic geometry, and apply it to these mixtures of ranking models to establish generic identifiability. The framework can be applied more broadly to other learning models and may be of independent interest.

  • Provable training set debugging for linear regression

    by Xiaomin Zhang, Xiaojin Zhu, Po-Ling Loh

  • Open Access

    Provable Training Set Debugging for Linear Regression

    by Xiaomin Zhang, Xiaojin Zhu, Po-Ling Loh

    We investigate problems in penalized $M$-estimation, inspired by applications in machine learning debugging. Data are collected from two pools, one containing data with possibly contaminated labels, and the other which is known to contain only cleanly labeled points. We first formulate a general statistical algorithm for identifying buggy points and provide rigorous theoretical guarantees under the assumption that the data follow a linear model. We then present two case studies to illustrate the results of our general theory and the dependence of our estimator on clean versus buggy points. We further propose an algorithm for tuning parameter selection of our Lasso-based algorithm and provide corresponding theoretical guarantees. Finally, we consider a two-person "game" played between a bug generator and a debugger, where the debugger can augment the contaminated data set with cleanly labeled versions of points in the original data pool. We establish a theoretical result showing a sufficient condition under which the bug generator can always fool the debugger. Nonetheless, we provide empirical results showing that such a situation may not occur in practice, making it possible for natural augmentation strategies combined with our Lasso debugging algorithm to succeed.

  • Open Access

    PBoS: Probabilistic Bag-of-Subwords for Generalizing Word Embedding

    by Zhao Jinman, Shawn Zhong, Xiaomin Zhang, Yingyu Liang

    We look into the task of \emph{generalizing} word embeddings: given a set of pre-trained word vectors over a finite vocabulary, the goal is to predict embedding vectors for out-of-vocabulary words, \emph{without} extra contextual information. We rely solely on the spellings of words and propose a model, along with an efficient algorithm, that simultaneously models subword segmentation and computes subword-based compositional word embedding. We call the model probabilistic bag-of-subwords (PBoS), as it applies bag-of-subwords for all possible segmentations based on their likelihood. Inspections and affix prediction experiment show that PBoS is able to produce meaningful subword segmentations and subword rankings without any source of explicit morphological knowledge. Word similarity and POS tagging experiments show clear advantages of PBoS over previous subword-level models in the quality of generated word embeddings across languages.

  • Research on Multi-source Data Fusion Technology Under Power Cloud Platform

    by Xiaomin Zhang, Qianjun Wu, Xiaolong Wang, Yuhang Chen

  • DOA estimation of multi-component LFM in complex environment using ESPRIT based on FRFT

    by Han Chong, Zhang Xiaomin

    Linear frequency modulation (LFM) signals are widely used in information systems. However, using traditional array signal process couldn't commendably estimate DOA of LFM signal, because which is a non-stationary signal. In this paper, the proposed method firstly applied the fractional Fourier Transform (FRFT) to construct the LFM signals array model, in which time-variant steering vector is changed into time-invariant one and wideband LFM signals are converted to narrowband stationary ones. Afterwards, a new improved ESPRIT method was proposed of DOA estimation which sufficiently made use of correlation and cross correlation information of covariance matrix to construct the new matrix. Then, the DOAs of coherent and non-coherent LFM signals are estimated by the signal parameters via a new improved rotation invariance technique (ESPRIT). Simulation results can not only demonstrate the effectiveness of this method, but also achieve high estimation accuracy.