Author name cluster

Zhen Zhu

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.

8 papers

1 author row

AAAI Conference 2026 Conference Paper

Dual Graph Disambiguation for Multi-Instance Partial-Label Learning

Zhen Zhu
Kai Tang
Songhe Feng
Yixuan Tang
Haobo Wang
Gengyu Lyu
Cheng Peng
Yining Sun

In multi-instance partial label learning (MIPL), each sample is a bag of multiple instances linked to a candidate label set containing one true and multiple false labels, yielding inexact supervision in both instance features and label space. However, existing works adopt decoupled approaches that focus exclusively on either instance-level feature fusion or label-level disambiguation, failing to fully exploit the intrinsic dependencies between these two spaces. To overcome this limitation, graph-based methods are widely recognized as a powerful paradigm in weakly supervised learning, yet their success hinges on reliable features—precisely what MIPL lacks due to instance-level noise. To bridge this gap, we propose DualG, a novel framework that simultaneously addresses feature learning and label disambiguation through dual-level graph propagation. Specifically, we construct dual relevance graphs at both the bag and instance levels. At the bag level, we build a similarity graph based on fused feature representations; at the instance level, we employ attention scores to filter out irrelevant instances and construct a reliable instance-level relevance graph. These complementary graphs enable our joint label disambiguation framework to simultaneously address inexact supervision signals in both instance space and label space. Experimental results on five benchmark datasets demonstrate that DualG outperforms existing MIPL and partial label learning methods, validating its effectiveness and superiority.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

AF-UMC: An Alignment-Free Fusion Framework for Unaligned Multi-View Clustering

Bohang Sun
Yuena Lin
Tao Yang
Zhen Zhu
Zhen Yang
Gengyu Lyu

The Unaligned Multi-view Clustering (UMC) aims to learn a discriminative cluster structure from unaligned multi-view data, where the features of samples are not completely aligned across multiple views. Most existing methods usually prioritize employing various alignment strategies to align sample representations across views and then conduct cross-view fusion on aligned representations for subsequent clustering. However, due to the heterogeneity of representations across different views, these alignment strategies often fail to achieve ideal view-alignment results, inevitably leading to unreliable alignment-based fusion. To address this issue, we propose an alignment-free consistency fusion framework named AF-UMC, which bypasses the traditional view-alignment operation and directly extracts consistent representations from each view to perform global cross-view consistency fusion. Specifically, we first construct a cross-view consistent basis space by a cross-view reconstruction loss and a designed Structural Clarity Regularization (SCR), where autoencoders extract consistent representations from each view through projecting view-specific data to the constructed basis space. Afterwards, these extracted representations are globally pulled together for further cross-view fusion according to a designed Instance Global Contrastive Fusion (IGCF). Compared with previous methods, AF-UMC directly extracts consistent representations from each view for global fusion instead of alignment for fusion, which significantly mitigates the degraded fusion performance caused by undesired view-alignment results while greatly reducing algorithm complexity and enhancing its efficiency. Extensive experiments on various datasets demonstrate that our AF-UMC exhibits superior performance against other state-of-the-art methods.

PDF Details

TMLR Journal 2025 Journal Article

TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models

Yao Xiao
Qiqian Fu
Heyi Tao
Yuqun Wu
Zhen Zhu
Derek Hoiem

Image-text models excel at image-level tasks but struggle with detailed visual understanding. While these models provide strong visual-language alignment, segmentation models like SAM2 offer precise spatial boundaries for objects. To this end, we propose TextRegion, a simple, effective, and training-free framework that combines the strengths of image-text models and SAM2 to generate powerful text-aligned region tokens. These tokens enable detailed visual understanding while preserving open-vocabulary capabilities. They can be directly applied to various downstream tasks, including open-world semantic segmentation, referring expression comprehension, and grounding. We conduct extensive evaluations and consistently achieve superior or competitive performance compared to state-of-the-art training-free methods. Additionally, our framework is compatible with many image-text models, making it highly practical and easily extensible as stronger models emerge. Code is available at: https://github.com/avaxiao/TextRegion.

PDF Details

TMLR Journal 2024 Journal Article

Continual Learning in Open-vocabulary Classification with Complementary Memory Systems

Zhen Zhu
Weijie Lyu
Yao Xiao
Derek Hoiem

We introduce a method for flexible and efficient continual learning in open-vocabulary image classification, drawing inspiration from the complementary learning systems observed in human cognition. Specifically, we propose to combine predictions from a CLIP zero-shot model and the exemplar-based model, using the zero-shot estimated probability that a sample's class is within the exemplar classes. We also propose a ``tree probe'' method, an adaption of lazy learning principles, which enables fast learning from new examples with competitive accuracy to batch-trained linear models. We test in data incremental, class incremental, and task incremental settings, as well as ability to perform flexible inference on varying subsets of zero-shot and learned categories. Our proposed method achieves a good balance of learning speed, target task effectiveness, and zero-shot effectiveness. Code is available at https://github.com/jessemelpolio/TreeProbe.

PDF Details

AAAI Conference 2022 Conference Paper

MobileFaceSwap: A Lightweight Framework for Video Face Swapping

Zhiliang Xu
Zhibin Hong
Changxing Ding
Zhen Zhu
Junyu Han
Jingtuo Liu
Errui Ding

Advanced face swapping methods have achieved appealing results. However, most of these methods have many parameters and computations, which makes it challenging to apply them in real-time applications or deploy them on edge devices like mobile phones. In this work, we propose a lightweight Identity-aware Dynamic Network (IDN) for subject-agnostic face swapping by dynamically adjusting the model parameters according to the identity information. In particular, we design an efficient Identity Injection Module (IIM) by introducing two dynamic neural network techniques, including the weights prediction and weights modulation. Once the IDN is updated, it can be applied to swap faces given any target image or video. The presented IDN contains only 0. 50M parameters and needs 0. 33G FLOPs per frame, making it capable for real-time video face swapping on mobile phones. In addition, we introduce a knowledge distillationbased method for stable training, and a loss reweighting module is employed to obtain better synthesized results. Finally, our method achieves comparable results with the teacher models and other state-of-the-art methods.

PDF Details

JBHI Journal 2022 Journal Article

ULECGNet: An Ultra-Lightweight End-to-End ECG Classification Neural Network

Jianbiao Xiao
Jiahao Liu
Huanqi Yang
Qingsong Liu
Ning Wang
Zhen Zhu
Yulong Chen
Yu Long

ECG classification is a key technology in intelligent electrocardiogram (ECG) monitoring. In the past, traditional machine learning methods such as support vector machine (SVM) and K-nearest neighbor (KNN) have been used for ECG classification, but with limited classification accuracy. Recently, the end-to-end neural network has been used for ECG classification and shows high classification accuracy. However, the end-to-end neural network has large computational complexity including a large number of parameters and operations. Although dedicated hardware such as field-programmable gate array (FPGA) and application-specific integrated circuit (ASIC) can be developed to accelerate the neural network, they result in large power consumption, large design cost, or limited flexibility. In this work, we have proposed an ultra-lightweight end-to-end ECG classification neural network that has extremely low computational complexity (∼8. 2k parameters & ∼227k multiplication/addition operations) and can be squeezed into a low-cost microcontroller (MCU) such as MSP432 while achieving 99. 1% overall classification accuracy. This outperforms the state-of-the-art ECG classification neural network. Implemented on MSP432, the proposed design consumes only 0. 4 mJ and 3. 1 mJ per heartbeat classification for normal and abnormal heartbeats respectively for real-time ECG classification.

Details DOI

AAAI Conference 2021 Conference Paper

FaceController: Controllable Attribute Editing for Face in the Wild

Zhiliang Xu
Xiyu Yu
Zhibin Hong
Zhen Zhu
Junyu Han
Jingtuo Liu
Errui Ding
Xiang Bai

Face attribute editing aims to generate faces with one or multiple desired face attributes manipulated while other details are preserved. Unlike prior works such as GAN inversion, which has an expensive reverse mapping process, we propose a simple feed-forward network to generate high-fidelity manipulated faces. By simply employing some existing and easy-obtainable prior information, our method can control, transfer, and edit diverse attributes of faces in the wild. The proposed method can consequently be applied to various applications such as face swapping, face relighting, and makeup transfer. In our method, we decouple identity, expression, pose, and illumination using 3D priors; separate texture and colors by using region-wise style codes. All the information is embedded into adversarial learning by our identity-style normalization module. Disentanglement losses are proposed to enhance the generator to extract information independently from each attribute. Comprehensive quantitative and qualitative evaluations have been conducted. In a single framework, our method achieves the best or competitive scores on a variety of face applications.

PDF Details

YNICL Journal 2019 Journal Article

Deep/mixed cerebral microbleeds are associated with cognitive dysfunction through thalamocortical connectivity disruption: The Taizhou Imaging Study

Yingzhe Wang
Yanfeng Jiang
Chen Suo
Ziyu Yuan
Kelin Xu
Qi Yang
Weijun Tang
Kexun Zhang

BACKGROUND: Cerebral microbleeds (CMBs) are considered to be risk factors for cognitive dysfunction. The specific pathology and clinical manifestations of CMBs are different based on their locations. We investigated the association between CMBs at different locations and cognitive dysfunction and explored the potential underlying pathways in a rural Han Chinese population. METHODS: We used baseline data from 562 community-dwelling adults (55-65 years old) in the Taizhou Imaging Study between 2013 and 2015. All individuals underwent multimodal brain magnetic resonance imaging (MRI) and 444 subjects completed neuropsychological tests: the Mini-Mental Status Examination and the Montreal Cognitive Assessment. Multinomial logistic regression was used to estimate the association between CMBs and cognitive dysfunction. The volume of brain regions and white matter microstructure were analyzed using Freesurfer and tract-based spatial statistics, respectively. RESULTS: CMBs were detected in 104 individuals (18.5%) in our study. Multinomial logistic regression found deep/mixed CMBs were associated with global cognitive dysfunction (OR 3.52; 95% CI 1.21 to 10.26), whereas lobar CMBs (OR 1.76; 95% CI 0.56 to 5.53) were not. Quantification of multimodal brain MRI showed that deep/mixed CMBs were accompanied by decreased thalamic volume and loss of fractional anisotropy of bilateral anterior thalamic radiations. CONCLUSION: Deep/mixed CMBs were associated with cognitive dysfunction in this Chinese cross-sectional study. Disruption of thalamocortical connectivity might be a potential pathway underlying this relationship.

Details DOI