Author name cluster

Xiang Yu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

2 author rows

EAAI Journal 2026 Journal Article

Numerical spiking neural membrane systems with dendritic spines for diagnosis of infectious spondylitis on Magnetic Resonance Images

Hongyan Zhang
Qiang Zhang
Jin Wang
Xiang Yu
Yang Li
Xiyu Liu
Jie Xue

As a branch of the third-generation neural network, the spiking neural membrane system has strong parallelism and low energy consumption. It has achieved success in pattern recognition, combinatorial optimization, power system control and robotics. However, traditional systems rely only on neuron rules for signal processing and transmission, and lack long-term memory. Long-term memory is an important function for biological neurons to achieve learning behavior. To address this limitation, we propose an innovative numerical spiking neural membrane system with dendritic spines, which enables neurons to retain and amplify important information. The system contains four neuron populations for identifying, memorizing, enhancing, and evaluating local salient features, respectively, and can be flexibly integrated into complex integrated membrane systems. In this study, a novel integrated membrane system is designed, which can extract key details from magnetic resonance images (MRI) using neurons, and enhance the salient features using neurons with dendritic spines, so as to improve the accuracy and efficiency of spondylitis diagnosis. The experimental results show that the system outperforms the current state-of-the-art deep learning network and four traditional classifiers in distinguishing tuberculous spondylitis from brucellar spondylitis, highlighting its potential in practical clinical applications.

Details DOI

EAAI Journal 2025 Journal Article

A temporal cross-contrastive self-supervised learning framework for high-speed train bearing fault diagnosis: addressing limited labeling and speed variability

Yuyan Li
Tiantian Wang
Jingsong Xie
Jinsong Yang
Tongyang Pan
Buzhao Niu
Xiang Yu

High-speed train (HST) bogie bearings operating under variable speed conditions exhibit significant domain distribution shifts. Moreover, the scarcity of labeled data in HST systems significantly compromises the accuracy and generalization capability of intelligent fault diagnosis methods. To address these challenges, we propose a novel self-supervised learning framework based on temporal cross-contrastive prediction (TCCP). In the upstream pretext task, an autoregressive prediction module is designed to learn domain-invariant representations from temporal data. Furthermore, we introduce a cross-prediction module to enhance the robustness of these domain-invariant representations. The temporal contrastive module is jointly optimized with the cross-prediction and autoregressive prediction modules to learn robust discriminative representations. In the downstream task, limited labeled data is utilized to fine-tune the pre-trained model for accurate fault diagnosis. The effectiveness of the proposed TCCP framework was extensively validated using both a public variable-speed bearing dataset and a self-built variable-speed HST bogie bearing dataset under limited labeled sample conditions. Experimental results demonstrate that our proposed method achieves superior fault diagnosis performance, yielding improvements in accuracy ranging from 0. 86 % to 7. 36 % on the HST bogie bearing dataset.

Details DOI

ICML Conference 2025 Conference Paper

Multivariate Conformal Selection

Tian Bai 0010
Yue Zhao
Xiang Yu
Archer Y. Yang

Selecting high-quality candidates from large datasets is critical in applications such as drug discovery, precision medicine, and alignment of large language models (LLMs). While Conformal Selection (CS) provides rigorous uncertainty quantification, it is limited to univariate responses and scalar criteria. To address this, we propose Multivariate Conformal Selection (mCS), a generalization of CS designed for multivariate response settings. Our method introduces regional monotonicity and employs multivariate nonconformity scores to construct conformal $p$-values, enabling finite-sample False Discovery Rate (FDR) control. We present two variants: $\texttt{mCS-dist}$, using distance-based scores, and $\texttt{mCS-learn}$, which learns optimal scores via differentiable optimization. Experiments on simulated and real-world datasets demonstrate that mCS significantly improves selection power while maintaining FDR control, establishing it as a robust framework for multivariate selection tasks.

Details

EAAI Journal 2024 Journal Article

An improved medical image segmentation framework with Channel-Height-Width-Spatial attention module

Xiang Yu
Hongbo Guo
Ying Yuan
Wenjia Guo
Xia Yang
Hui Xu
Yanqing Kong
Yudong Zhang

This paper presents an improved version of the U-Net segmentation framework for medical image segmentation, called CHWS-UNet. To build the proposed framework CHWS-UNet, we first develop a novel lightweight channel attention module called LCAM, based on which we further propose the Channel-Height-Width-Spatial (CHWS) attention module for channel, height, width, and spatial dimension-level feature refinement. Our CHWS-UNet is constructed by integrating the proposed CHWS attention modules into the shortcut paths between the encoder and the decoder stem. To justify the effectiveness of the proposed modules and networks, we then carried out extensive experiments on four public medical image datasets, including BUSI, ISIC2017, ISIC2018, PH and a proprietary uterus lesion ultrasound dataset from Shenzhen Maternity and Child Healthcare Hospital. The results show that the proposed attention module can significantly improve the performance of baseline models, even on small medical image datasets, without introducing noticeable parameters and computational costs. Further, the proposed segmentation framework can achieve promising performance compared to edge-cutting frameworks. The code can be found at CHWS-UNet.

Details DOI

TMLR Journal 2023 Journal Article

Semi-Supervised Single Domain Generalization with Label-Free Adversarial Data Augmentation

Ronghang Zhu
Xiang Yu
Sheng Li

Domain generalization (DG) has attracted increasing attention recently, as it seeks to improve the generalization ability of visual recognition models to unseen target domains. DG leverages multiple source domains for model training, while single domain generalization (SDG) further restricts such setting by exploiting only a single source domain. Nevertheless, both DG and SDG assume that the source domains are fully labeled, which might not be practical in many real world scenarios. In this paper, we present a new problem, i.e., semi-supervised single domain generalization (SS-SDG), which aims to train a model with a partially labeled single source domain to generalize to multiple unseen testing domains. We propose an effective framework to address this problem. In particular, we design a label-free adversarial data augmentation strategy to diversify the source domain, and propose a novel multi-pair FixMatch loss to generalize classifiers to unseen testing domains. Extensive experiments on OfficeHome, PACS and DomainNet20 datasets show that our method surpasses the latest SDG and semi-supervised methods. Moreover, on PACS and DomainNet20, our method approaches the fully supervised ERM upper bound within $5\%$ gap, but only uses less than $8\%$ of the labels.

PDF Details

NeurIPS Conference 2017 Conference Paper

Learning Efficient Object Detection Models with Knowledge Distillation

Guobin Chen
Wongun Choi
Xiang Yu
Tony Han
Manmohan Chandraker

Despite significant accuracy improvement in convolutional neural networks (CNN) based object detectors, they often require prohibitive runtimes to process an image for real-time applications. State-of-the-art models often use very deep networks with a large number of floating point operations. Efforts such as model compression learn compact models with fewer number of parameters, but with much reduced accuracy. In this work, we propose a new framework to learn compact and fast ob- ject detection networks with improved accuracy using knowledge distillation [20] and hint learning [34]. Although knowledge distillation has demonstrated excellent improvements for simpler classification setups, the complexity of detection poses new challenges in the form of regression, region proposals and less voluminous la- bels. We address this through several innovations such as a weighted cross-entropy loss to address class imbalance, a teacher bounded loss to handle the regression component and adaptation layers to better learn from intermediate teacher distribu- tions. We conduct comprehensive empirical evaluation with different distillation configurations over multiple datasets including PASCAL, KITTI, ILSVRC and MS-COCO. Our results show consistent improvement in accuracy-speed trade-offs for modern multi-class detection models.

PDF Details

IJCAI Conference 2016 Conference Paper

Nonlinear Hierarchical Part-Based Regression for Unconstrained Face Alignment

Xiang Yu
Zhe Lin
Shaoting Zhang
Dimitris N. Metaxas

Non-linear regression is a fundamental and yet under-developing methodology in solving many problems in Artificial Intelligence. The canonical control and predictions mostly utilize linear models or multi-linear models. However, due to the high non-linearity of the systems, those linear prediction models cannot fully cover the complexity of the problems. In this paper, we propose a robust two-stage hierarchical regression approach, to solve a popular Human-Computer Interaction, the unconstrained face-in-the-wild keypoint detection problem for computers. The environment is the still images, videos and live camera streams from machine vision. We firstly propose a holistic regression model to initialize the face fiducial points under different head pose assumptions. Second, to reduce local shape variance, a hierarchical part-based regression method is further proposed to refine the global regression output. Experiments on several challenging faces-in-the-wild datasets demonstrate the consistently better accuracy of our method, when compared to the state-of-the-art.

PDF Details