Author name cluster

Yingying 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.

10 papers

1 author row

AAAI Conference 2026 Conference Paper

AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detection

Zhaopeng Gu
Bingke Zhu
Guibo Zhu
Yingying Chen
Wei Ge
Ming Tang
Jinqiao Wang

Anomaly detection is a critical task across numerous domains and modalities, yet existing methods are often highly specialized, limiting their generalizability. These specialized models, tailored for specific anomaly types like textural defects or logical errors, typically exhibit limited performance when deployed outside their designated contexts. To overcome this limitation, we propose AnomalyMoE, a novel and universal anomaly detection framework based on a Mixture-of-Experts (MoE) architecture. Our key insight is to decompose the complex anomaly detection problem into three distinct semantic hierarchies: local structural anomalies, component-level semantic anomalies, and global logical anomalies. AnomalyMoE correspondingly employs three dedicated expert networks at the patch, component, and global levels, and is specialized in reconstructing features and identifying deviations at its designated semantic level. This hierarchical design allows a single model to concurrently understand and detect a wide spectrum of anomalies. Furthermore, we introduce an Expert Information Repulsion (EIR) module to promote expert diversity and an Expert Selection Balancing (ESB) module to ensure the comprehensive utilization of all experts. Experiments on 8 challenging datasets spanning industrial imaging, 3D point clouds, medical imaging, video surveillance, and logical anomaly detection demonstrate that AnomalyMoE establishes new state-of-the-art performance, significantly outperforming specialized methods in their respective domains.

PDF Details DOI

EAAI Journal 2026 Journal Article

Multisource space-frequency joint learning: A novel paradigm for ultrasound image quality assessment

Tuo Liu
Xuan Zhang
Yingying Chen
Xuejuan Wang
Yang Chen
Rongjun Ge
Faqin Lv
Guang-Quan Zhou

Ultrasound image quality is critical to accurate diagnosis in clinical practice. However, assessing the ultrasound image quality is challenging due to the various interferences and the inherent low spatial resolution. In this study, we propose a novel multisource space-frequency joint learning (MSJL) paradigm for ultrasound image quality assessment (IQA). This paradigm imitates clinicians’ self-guided exploration process by integrating self-supervised and transfer learning, leveraging contextual cues and patterns spontaneously perceived from ultrasound images and natural images for piloted knowledge. Mainly, MSJL advances soft masked frequency modeling (SMFM) to separate global style and local detail perceptions in unlabeled ultrasound images, contributing to the awareness of quality-related contours and texture patterns by recovering the lost spectrum components from filtered image. Besides, MSJL fuses encoders pre-trained by SMFM with an encoder pre-trained on large amounts of natural images for general spatial patterns acquirement. Moreover, we propose frequency-aware fusion (FAF) to adaptively reweight the components within and between features from a frequency perspective, thus increasing the reliability of final quality predictions. Experimental results on three datasets show that MSJL surpasses the state-of-the-art methods on multiple metrics of ultrasound IQA. In addition, our paradigm exhibits the potential for generalization to similar tasks. The code is publicly available via URL.

Details DOI

AAAI Conference 2026 Conference Paper

Quality-Aware Language-Conditioned Local Auto-Regressive Anomaly Synthesis and Detection

Long Qian
Bingke Zhu
Yingying Chen
Ming Tang
Jinqiao Wang

Despite substantial progress in anomaly synthesis, existing diffusion-based and coarse inpainting pipelines commonly suffer from structural deficiencies such as micro-structural discontinuities, limited semantic controllability, and inefficient generation. To overcome these limitations, we introduce ARAS, a language-conditioned, auto-regressive anomaly synthesis approach that precisely injects local, text-specified defects into normal images via token-anchored latent editing. Leveraging a hard-gated auto-regressive operator and a training-free, context-preserving masked sampling kernel, ARAS significantly enhances defect realism, preserves fine-grained material textures, and provides continuous semantic control over synthesized anomalies. Integrated within our Quality-Aware Re-weighted Anomaly Detection (QARAD) framework, we propose a dynamic weighting strategy that emphasizes high-quality synthetic samples by computing an image-text similarity score with a dual-encoder model. Extensive experiments across three datasets, MVTec AD, VisA, and BTAD, demonstrate that our QARAD outperforms SOTA methods in both image- and pixel-level anomaly detection tasks, achieving improved accuracy, robustness, and a 5× synthesis speedup compared to diffusion-based alternatives.

PDF Details DOI

TMLR Journal 2025 Journal Article

DisDet: Exploring Detectability of Backdoor Attack on Diffusion Models

Yang Sui
Huy Phan
Jinqi Xiao
Tianfang Zhang
Zijie Tang
Cong Shi
Yan Wang
Yingying Chen

In the exciting generative AI era, the diffusion model has emerged as a very powerful and widely adopted content-generation tool. Very recently, some pioneering works have shown the vulnerability of the diffusion model against backdoor attacks, calling for in-depth analysis and investigation of the security challenges. In this paper, we explore the detectability of the poisoned noise input for the backdoored diffusion models, an important performance metric yet little explored in the existing works. Starting from the perspective of a defender, we first analyze the distribution discrepancy of the trigger pattern in the existing diffusion backdoor attacks. Based on this finding, we propose a trigger detection mechanism that can effectively identify the poisoned input noise. Then, from the attack side, we propose a backdoor attack strategy that can learn the unnoticeable trigger to evade our proposed detection scheme. Our empirical evaluations across various diffusion models and datasets demonstrate the effectiveness of the proposed trigger detection and detection-evading attack strategy. For trigger detection, our distribution discrepancy-based solution can achieve a 100% detection rate for the Trojan triggers used in the existing works. For evading trigger detection, our proposed stealthy trigger design approach performs end-to-end learning to make the distribution of poisoned noise input approach that of benign noise, enabling nearly 100% detection pass rate with very high attack and benign performance for the backdoored diffusion models.

PDF Details

IJCAI Conference 2025 Conference Paper

FLARE: A Framework for Stellar Flare Forecasting Using Stellar Physical Properties and Historical Records

Bingke Zhu
Xiaoxiao Wang
Minghui Jia
Yihan Tao
Xiao Kong
Ali Luo
Yingying Chen
Ming Tang

Stellar flare events are critical observational samples for astronomical research; however, recorded flare events remain limited. Stellar flare forecasting can provide additional flare event samples to support research efforts. Despite this potential, no specialized models for stellar flare forecasting have been proposed to date. In this paper, we present extensive experimental evidence demonstrating that both stellar physical properties and historical flare records are valuable inputs for flare forecasting tasks. We then introduce FLARE (Forecasting Light-curve-based Astronomical Records via features Ensemble), the first-of-its-kind large model specifically designed for stellar flare forecasting. FLARE integrates stellar physical properties and historical flare records through a novel Soft Prompt Module and Residual Record Fusion Module. Experiments on the Kepler light curve dataset demonstrate that FLARE achieves superior performance compared to other methods across all evaluation metrics. Finally, we validate the forecast capability of our model through a comprehensive case study.

PDF Details DOI

AAAI Conference 2024 Conference Paper

AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models

Zhaopeng Gu
Bingke Zhu
Guibo Zhu
Yingying Chen
Ming Tang
Jinqiao Wang

Large Vision-Language Models (LVLMs) such as MiniGPT-4 and LLaVA have demonstrated the capability of understanding images and achieved remarkable performance in various visual tasks. Despite their strong abilities in recognizing common objects due to extensive training datasets, they lack specific domain knowledge and have a weaker understanding of localized details within objects, which hinders their effectiveness in the Industrial Anomaly Detection (IAD) task. On the other hand, most existing IAD methods only provide anomaly scores and necessitate the manual setting of thresholds to distinguish between normal and abnormal samples, which restricts their practical implementation. In this paper, we explore the utilization of LVLM to address the IAD problem and propose AnomalyGPT, a novel IAD approach based on LVLM. We generate training data by simulating anomalous images and producing corresponding textual descriptions for each image. We also employ an image decoder to provide fine-grained semantic and design a prompt learner to fine-tune the LVLM using prompt embeddings. Our AnomalyGPT eliminates the need for manual threshold adjustments, thus directly assesses the presence and locations of anomalies. Additionally, AnomalyGPT supports multi-turn dialogues and exhibits impressive few-shot in-context learning capabilities. With only one normal shot, AnomalyGPT achieves the state-of-the-art performance with an accuracy of 86.1%, an image-level AUC of 94.1%, and a pixel-level AUC of 95.3% on the MVTec-AD dataset.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Forecasting Asset Dependencies to Reduce Portfolio Risk

Haoren Zhu
Shih-Yang Liu
Pengfei Zhao
Yingying Chen
Dik Lun Lee

Financial assets exhibit dependence structures, i. e. , movements of their prices or returns show various correlations. Knowledge of assets’ price dependencies can help investors create a diversified portfolio, which reduces portfolio risk due to the high volatility of the financial market. Since asset dependency changes with time in complex patterns, asset dependency forecast is an essential problem in finance. In this paper, we organize pairwise assets dependencies in an Asset Dependency Matrix (ADM) and formulate the problem of assets dependencies forecast to predict the future ADM given a sequence of past ADMs. We propose a novel idea viewing a sequence of ADMs as a sequence of images to capture the spatial and temporal dependencies among the assets. Inspired by video prediction tasks, we develop a novel Asset Dependency Neural Network (ADNN) to tackle the ADM prediction problem. Experiments show that our proposed framework consistently outperforms the baselines on both future ADM prediction and portfolio risk reduction tasks.

PDF Details

AAAI Conference 2021 Conference Paper

Enabling Fast and Universal Audio Adversarial Attack Using Generative Model

Yi Xie
Zhuohang Li
Cong Shi
Jian Liu
Yingying Chen
Bo Yuan

Recently, the vulnerability of deep neural network (DNN)based audio systems to adversarial attacks has obtained increasing attention. However, the existing audio adversarial attacks allow the adversary to possess the entire user’s audio input as well as granting sufficient time budget to generate the adversarial perturbations. These idealized assumptions, however, make the existing audio adversarial attacks mostly impossible to be launched in a timely fashion in practice (e. g. , playing unnoticeable adversarial perturbations along with user’s streaming input). To overcome these limitations, in this paper we propose fast audio adversarial perturbation generator (FAPG), which uses generative model to generate adversarial perturbations for the audio input in a single forward pass, thereby drastically improving the perturbation generation speed. Built on the top of FAPG, we further propose universal audio adversarial perturbation generator (UAPG), a scheme to craft universal adversarial perturbation that can be imposed on arbitrary benign audio input to cause misclassification. Extensive experiments on DNN-based audio systems show that our proposed FAPG can achieve high success rate with up to 214× speedup over the existing audio adversarial attack methods. Also our proposed UAPG generates universal adversarial perturbations that can achieve much better attack performance than the state-of-the-art solutions.

PDF Details

AAAI Conference 2020 Conference Paper

Progressive Bi-C3D Pose Grammar for Human Pose Estimation

Lu Zhou
Yingying Chen
Jinqiao Wang
Hanqing Lu

In this paper, we propose a progressive pose grammar network learned with Bi-C3D (Bidirectional Convolutional 3D) for human pose estimation. Exploiting the dependencies among the human body parts proves effective in solving the problems such as complex articulation, occlusion and so on. Therefore, we propose two articulated grammars learned with Bi-C3D to build the relationships of the human joints and exploit the contextual information of human body structure. Firstly, a local multi-scale Bi-C3D kinematics grammar is proposed to promote the message passing process among the locally related joints. The multi-scale kinematics grammar excavates different levels human context learned by the network. Moreover, a global sequential grammar is put forward to capture the long-range dependencies among the human body joints. The whole procedure can be regarded as a local-global progressive reﬁnement process. Without bells and whistles, our method achieves competitive performance on both MPII and LSP benchmarks compared with previous methods, which conﬁrms the feasibility and effectiveness of C3D in information interactions.

PDF Details

AAAI Conference 2018 Conference Paper

Progressive Cognitive Human Parsing

Bingke Zhu
Yingying Chen
Ming Tang
Jinqiao Wang

Human parsing is an important task for human-centric understanding. Generally, two mainstreams are used to deal with this challenging and fundamental problem. The ﬁrst one is employing extra human pose information to generate hierarchical parse graph to deal with human parsing task. Another one is training an end-to-end network with the semantic information in image level. In this paper, we develop an end-to-end progressive cognitive network to segment human parts. In order to establish a hierarchical relationship, a novel component-aware region convolution structure is proposed. With this structure, latter layers inherit prior component information from former layers and pay its attention to a ﬁner component. In this way, we deal with human parsing as a progressive recognition task, that is, we ﬁrst locate the whole human and then segment the hierarchical components gradually. The experiments indicate that our method has a better location capacity for the small objects and a better classiﬁcation capacity for the large objects. Moreover, our framework can be embedded into any fully convolutional network to enhance the performance signiﬁcantly.

PDF Details