Author name cluster

Junxiang Chen

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.

9 papers

2 author rows

JBHI Journal 2026 Journal Article

CAM-Interacted Vision GNN for Multi-Label Medical Images

Jingchao Wang
Baoyao Yang
Siqi Liu
Xiaoqi Zheng
Wenbin Yao
Junxiang Chen

Vision Graph Neural Network (ViG) is designed to recognize different objects through graph-level processing. However, ViG constructs graphs with appearance-level neighbors and neglects the category semantic. The oversight results in the unintentional connection of patches that belong to different objects, thus affecting the distinctiveness of categories in multi-label medical image learning. Since the pixel-level annotations for images are not easily available, category-aware graphs can not be directly built. To solve this problem, we consider localizing category-specific regions using Class Activation Maps (CAMs), an effective way to highlight regions belonging to each category without requiring manual annotations. Specifically, we propose a CAM-interacted Vision GNN (CiV-GNN), in which category-aware graphs are formed to perform intra-category graph processing. CIV-GNN includes a Class-activated Patch Division (CAPD) module, which introduces CAMs as guidance for category-aware graph building. Furthermore, we develop a Multi-graph Interactive Processing (MIP) module to model the relations between category-aware graphs, promoting inter-category interaction learning. Experimental results show that CiV-GNN performs well in surgical tool localization and multi-label medical image classification. Specifically, for m2cai16-localization, CiV-GNN exhibits a 1. 43% and 7. 02% improvement in mAP50 and mAP50-95, respectively, compared to YOLOv8.

Details DOI

ECAI Conference 2025 Conference Paper

Unlocking the Potential of mLLMs: Enhancing Video-Text Retrieval Through Caption Supplementation and Conical Embedding Optimization

Baoyao Yang
Junxiang Chen
Wenbin Yao

The burgeoning field of video-text retrieval has witnessed significant advancements with the advent of deep learning. However, understanding and matching textual descriptions and video data remains a formidable challenge due to the large information gap across textual and video modalities. As observed, the caption of a video is commonly under-described, lacking expressions of minor characters or local details. Some recent advances have attempted to leverage multimodal Large Language Model (mLLM) to bridge the comprehension gap. However, mLLMs’ potential in enhancing video-text retrieval (VTR) is understudied. This paper aims to fill this research vacancy, analyzing the practical significance and model preferences for utilizing mLLMs in VTR enhancement, as well as investigating the effective integration of mLLM-derived information into the retrieval learning. Based on our analytical insights, we innovatively propose treating mLLM as caption supplements rather than substitutes to bridge the expression gap across modalities. To achieve better cross-modal alignment, we systematically generate diverse variations of videos to construct an elastic visual space. By treating mLLM-supplemented captions as out-of-space points, cross-modal representation learning is accomplished through the optimization of a conical-like representation space. Our model achieves state-of-the-art results on various benchmarks, including MSR-VTT, MSVD, and DiDeMo, and analytical experiments suggest appropriate prompt proposals and indicate our method’s robustness to different mLLMs.

Details

JBHI Journal 2023 Journal Article

Automatic Representative Frame Selection and Intrathoracic Lymph Node Diagnosis With Endobronchial Ultrasound Elastography Videos

Mingxing Xu
Junxiang Chen
Jin Li
Xinxin Zhi
Wenrui Dai
Jiayuan Sun
Hongkai Xiong

Endobronchial ultrasound (EBUS) elastography videos have shown great potential to supplement intrathoracic lymph node diagnosis. However, it is laborious and subjective for the specialists to select the representative frames from the tedious videos and make a diagnosis, and there lacks a framework for automatic representative frame selection and diagnosis. To this end, we propose a novel deep learning framework that achieves reliable diagnosis by explicitly selecting sparse representative frames and guaranteeing the invariance of diagnostic results to the permutations of video frames. Specifically, we develop a differentiable sparse graph attention mechanism that jointly considers frame-level features and the interactions across frames to select sparse representative frames and exclude disturbed frames. Furthermore, instead of adopting deep learning-based frame-level features, we introduce the normalized color histogram that considers the domain knowledge of EBUS elastography images and achieves superior performance. To our best knowledge, the proposed framework is the first to simultaneously achieve automatic representative frame selection and diagnosis with EBUS elastography videos. Experimental results demonstrate that it achieves an average accuracy of 81. 29% and area under the receiver operating characteristic curve (AUC) of 0. 8749 on the collected dataset of 727 EBUS elastography videos, which is comparable to the performance of the expert-based clinical methods based on manually-selected representative frames.

Details DOI

JBHI Journal 2022 Journal Article

Hierarchical Amortized GAN for 3D High Resolution Medical Image Synthesis

Li Sun
Junxiang Chen
Yanwu Xu
Mingming Gong
Ke Yu
Kayhan Batmanghelich

Generative Adversarial Networks (GAN) have many potential medical imaging applications, including data augmentation, domain adaptation, and model explanation. Due to the limited memory of Graphical Processing Units (GPUs), most current 3D GAN models are trained on low-resolution medical images, these models either cannot scale to high-resolution or are prone to patchy artifacts. In this work, we propose a novel end-to-end GAN architecture that can generate high-resolution 3D images. We achieve this goal by using different configurations between training and inference. During training, we adopt a hierarchical structure that simultaneously generates a low-resolution version of the image and a randomly selected sub-volume of the high-resolution image. The hierarchical design has two advantages: First, the memory demand for training on high-resolution images is amortized among sub-volumes. Furthermore, anchoring the high-resolution sub-volumes to a single low-resolution image ensures anatomical consistency between sub-volumes. During inference, our model can directly generate full high-resolution images. We also incorporate an encoder with a similar hierarchical structure into the model to extract features from the images. Experiments on 3D thorax CT and brain MRI demonstrate that our approach outperforms state of the art in image generation. We also demonstrate clinical applications of the proposed model in data augmentation and clinical-relevant feature extraction.

Details DOI

ICLR Conference 2020 Conference Paper

Explanation by Progressive Exaggeration

Sumedha Singla
Brian Pollack
Junxiang Chen
Kayhan Batmanghelich

As machine learning methods see greater adoption and implementation in high stakes applications such as medical image diagnosis, the need for model interpretability and explanation has become more critical. Classical approaches that assess feature importance (eg saliency maps) do not explain how and why a particular region of an image is relevant to the prediction. We propose a method that explains the outcome of a classification black-box by gradually exaggerating the semantic effect of a given class. Given a query input to a classifier, our method produces a progressive set of plausible variations of that query, which gradually change the posterior probability from its original class to its negation. These counter-factually generated samples preserve features unrelated to the classification decision, such that a user can employ our method as a ``tuning knob'' to traverse a data manifold while crossing the decision boundary. Our method is model agnostic and only requires the output value and gradient of the predictor with respect to its input.

Details

AAAI Conference 2020 Conference Paper

Generative-Discriminative Complementary Learning

Yanwu Xu
Mingming Gong
Junxiang Chen
Tongliang Liu
Kun Zhang
Kayhan Batmanghelich

The majority of state-of-the-art deep learning methods are discriminative approaches, which model the conditional distribution of labels given inputs features. The success of such approaches heavily depends on high-quality labeled instances, which are not easy to obtain, especially as the number of candidate classes increases. In this paper, we study the complementary learning problem. Unlike ordinary labels, complementary labels are easy to obtain because an annotator only needs to provide a yes/no answer to a randomly chosen candidate class for each instance. We propose a generative-discriminative complementary learning method that estimates the ordinary labels by modeling both the conditional (discriminative) and instance (generative) distributions. Our method, we call Complementary Conditional GAN (CCGAN), improves the accuracy of predicting ordinary labels and is able to generate high-quality instances in spite of weak supervision. In addition to the extensive empirical studies, we also theoretically show that our model can retrieve the true conditional distribution from the complementarilylabeled data.

PDF Details

AAAI Conference 2020 Conference Paper

Weakly Supervised Disentanglement by Pairwise Similarities

Junxiang Chen
Kayhan Batmanghelich

Recently, researches related to unsupervised disentanglement learning with deep generative models have gained substantial popularity. However, without introducing supervision, there is no guarantee that the factors of interest can be successfully recovered (Locatello et al. 2018). Motivated by a real-world problem, we propose a setting where the user introduces weak supervision by providing similarities between instances based on a factor to be disentangled. The similarity is provided as either a binary (yes/no) or real-valued label describing whether a pair of instances are similar or not. We propose a new method for weakly supervised disentanglement of latent variables within the framework of Variational Autoencoder. Experimental results demonstrate that utilizing weak supervision improves the performance of the disentanglement method substantially.

PDF Details

ICML Conference 2017 Conference Paper

Multiple Clustering Views from Multiple Uncertain Experts

Yale Chang
Junxiang Chen
Michael H. Cho
Peter J. Castaldi
Edwin K. Silverman
Jennifer G. Dy

Expert input can improve clustering performance. In today’s collaborative environment, the availability of crowdsourced multiple expert input is becoming common. Given multiple experts’ inputs, most existing approaches can only discover one clustering structure. However, data is multi-faced by nature and can be clustered in different ways (also known as views). In an exploratory analysis problem where ground truth is not known, different experts may have diverse views on how to cluster data. In this paper, we address the problem on how to automatically discover multiple ways to cluster data given potentially diverse inputs from multiple uncertain experts. We propose a novel Bayesian probabilistic model that automatically learns the multiple expert views and the clustering structure associated with each view. The benefits of learning the experts’ views include 1) enabling the discovery of multiple diverse clustering structures, and 2) improving the quality of clustering solution in each view by assigning higher weights to experts with higher confidence. In our approach, the expert views, multiple clustering structures and expert confidences are jointly learned via variational inference. Experimental results on synthetic datasets, benchmark datasets and a real-world disease subtyping problem show that our proposed approach outperforms competing baselines, including meta clustering, semi-supervised clustering, semi-crowdsourced clustering and consensus clustering.

Details

UAI Conference 2016 Conference Paper

A Generative Block-Diagonal Model for Clustering

Junxiang Chen
Jennifer G. Dy

Probabilistic mixture models are among the most important clustering methods. These models assume that the feature vectors of the samples can be described by a mixture of several components. Each of these components follows a distribution of a certain form. In recent years, there has been an increasing amount of interest and work in similarity-matrix-based methods. Rather than considering the feature vectors, these methods learn patterns by observing the similarity matrix that describes the pairwise relative similarity between each pair of samples. However, there are limited works in probabilistic mixture model for clustering with input data in the form of a similarity matrix. Observing this, we propose a generative model for clustering that finds the block-diagonal structure of the similarity matrix to ensure that the samples within the same cluster (diagonal block) are similar while the samples from different clusters (off-diagonal block) are less similar. In this model, we assume the elements in the similarity matrix follow one of beta distributions, depending on whether the element belongs to one of the diagonal blocks or to off-diagonal blocks. The assignment of the element to a block is determined by the cluster indicators that follow categorical distributions. Experiments on both synthetic and real data show that the performance of the proposed method is comparable to the state-of-the-art methods.

Details