Shuai Jiang

Shuai Jiang

Auto-generated profile, based on publicly available information

Shuai Jiang

School of Artificial Intelligence and Robotics, Hunan University, Changsha, Hunan, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 July 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
KHKai Hu
Kai Hu
SJShuai Jiang
Shuai Jiang
YZYuan Zhang
Yuan Zhang
XLXuanya Li
Xuanya Li
XGXieping Gao
Xieping Gao
Optical coherence tomography angiography (OCTA) has been widely used in ophthalmology in recent years due to its noninvasive and high resolution. In OCTA images, two biomarkers are extremely important for clinical diagnosis, i.e., foveal avascular zone (FAZ) and retinal vessel (RV), and RV has an implicit constraint on FAZ in position. In previous studies, the segmentation of the two biomarkers is naturally separated, which undoubtedly leads to the omission of such constraints between them. In this article, we propose a joint segmentation framework ( Joint-Seg ), a single-encoder and dual-decoder architecture, through which simultaneous FAZ and RV extractions from en-face OCTA images can be achieved. Specifically, the OCTA image is encoded through joint encoding and provides FAZ- or RV-related information to separate decoding branches through a feature adaptive filter (FAF). In the FAZ segmentation branch, we propose a feature alignment decoder block (FADB) to recover image details, especially boundaries. While in the RV segmentation branch, a multiscale soft fusion module (MSFM) is designed to adapt to different vessel thicknesses. Finally, we evaluate the proposed Joint-Seg on the OCTA-500 dataset, and the experimental results show that our Joint-Seg outperforms the state-of-the-art methods on both FAZ and RV segmentations and has fewer floating point operations (FLOPs) and parameters. The generalization experiments on four other datasets, i.e., OCTAGON, sFAZ, OCTA-25K, and ROSE, also demonstrate the portability and scalability of the proposed Joint-Seg framework. In addition, the noise analysis further shows good robustness of the proposed method against noise.

26 March 2025 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
YMYunfeng Ma
Yunfeng Ma
MLMin Liu
Min Liu
SJShuai Jiang
Shuai Jiang
XWXueping Wang
Xueping Wang
YBYuan Bian
Yuan Bian
YWYaonan Wang
Yaonan Wang
State-of-the-art defect segmentation methods rely on sufficient training data and struggle to generalize to unseen categories. Few-Shot Semantic Segmentation (FSS) is introduced to specifically address these issues. However, existing FSS models still face two challenges in the industry. (1) Defects usually present as weak features, resulting in incomplete segmentation. (2) Severe background interference often leads to incorrect segmentation. To tackle these problems, we propose the Multi-Context Aggregation Network (MCANet). Specifically, we design a Cross-Layer Multi-Level Feature Aggregation Module (CMAM). CMAM effectively aggregates discretely distributed multi-level defect features across different layers and guides the query image to perceive defects from the pixel level, which avoids incomplete segmentation caused by weak features. Additionally, a Foreground Correction Module (FCM) is developed, which is equipped with a dedicated background predictor (BP) and a foreground corrector (FC). BP places more emphasis on learning features from backgrounds rather than defects. FC achieves efficient feature ensemble and further suppresses the backgrounds misidentified as defects in CMAM. They collaborate to prevent incorrect segmentation caused by background interference. Extensive experiments demonstrate the effectiveness of our method. We achieve state-of-the-art results on both FSSD-12, a public benchmark FSS dataset for strip steel, and FSS-AEB, an FSS dataset for aero-engine blades. Specifically, with 1/5 support images, we achieve 64.6%/65.6% mIoU on FSSD-12 and 55.0%/57.8% mIoU on FSS-AEB.

22 May 2025 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Closed access
JZJingyu Zhou
Jingyu Zhou
MLMin Liu
Min Liu
YMYunfeng Ma
Yunfeng Ma
SJShuai Jiang
Shuai Jiang
YWYaonan Wang
Yaonan Wang
Unsupervised surface defect detection is gaining attention in quality assurance of industrial manufacturing. However, existing methods typically rely on single-view data, which will lead to imaging blind spots and poor discrimination of subtle defects due to the complex structures of industrial components. Therefore, this article proposes a novel multiview attention guided feature learning (MVAG-FL) approach, which offers two primary advantages. First, the MVAG-FL leverages intra-view and cross-view attention to adaptively integrate in-formation and effectively learns subtle defect features from mul-tiple perspectives. Second, a multilevel dual perturbation module, combining layer-wise jitter and bottleneck perturbation, is proposed to improve the robustness and performance of the MVAG-FL in a multiclass setting. Considering the requirement for global feature consistency of different perspectives and focusing on local defect regions, a global-local adaptive cosine loss is designed to align multiview features and amplify the difference between subtle and normal features. Experiments were conducted on the Real-IAD dataset with the multiclass setting, and the results show MVAG-FL outperforms the state-of-the-art multiview detection methods, with 1.2% image-level and 4.5% pixel-level AUROC improvements.

29 January 2026 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YMYunfeng Ma
Yunfeng Ma
MLMin Liu
Min Liu
SJShuai Jiang
Shuai Jiang
JZJingyu Zhou
Jingyu Zhou
YBYuan Bian
Yuan Bian
YWYaonan Wang
Yaonan Wang
Multimodal anomaly detection (MAD) aims to exploit both texture and spatial attributes to identify deviations from normal patterns in complex scenarios. However, zero-shot (ZS) settings arising from privacy concerns or confidentiality constraints present significant challenges to existing MAD methods. To address this issue, we introduce ZUMA, a training-free, Zero-shot Unified Multimodal Anomaly detection framework that unleashes CLIP’s cross-modal potential to perform ZS MAD. To mitigate the domain gap between CLIP’s pretraining space and point clouds, we propose cross-domain calibration (CDC), which efficiently bridges the manifold misalignment through source-domain semantic transfer and establishes a hybrid semantic space, enabling a joint embedding of 2D and 3D representations. Subsequently, ZUMA performs dynamic semantic interaction (DSI) to enable structural decoupling of anomaly regions in the high-dimensional embedding space constructed by CDC, where natural languages serve as semantic anchors to help DSI establish discriminative hyperplanes within hybrid modality representations. Within this framework, ZUMA enables plug-and-play detection of 2D, 3D or multimodal anomalies, without training or fine-tuning even for cross-dataset or incomplete-modality scenarios. Additionally, to further investigate the potential of the training-free ZUMA within the training-based paradigm, we develop ZUMA-FT, a fine-tuned variant that achieves notable improvements with minimal parameter trade-off. Extensive experiments are conducted on two MAD benchmarks, MVTec 3D-AD and Eyecandies. Notably, the training-free ZUMA achieves state-of-the-art (SOTA) performance on both datasets, outperforming existing ZS MAD methods, including training-based approaches. Moreover, ZUMA-FT further extends the performance boundary of ZUMA with only 6.75 M learnable parameters.

19 September 2025 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Closed access
SJShuai Jiang
Shuai Jiang
YMYunfeng Ma
Yunfeng Ma
JZJingyu Zhou
Jingyu Zhou
YBYuan Bian
Yuan Bian
YWYaonan Wang
Yaonan Wang
MLMin Liu
Min Liu
Multimodal industrial surface defect detection (MISDD) aims to identify and locate defect in industrial products by fusing RGB and 3-D modalities. This article focuses on modality-missing problems caused by uncertain sensors availability in MISDD. In this context, the fusion of multiple modalities encounters several troubles, including learning mode transformation and information vacancy. To this end, we first propose cross-modal prompt learning, which includes: 1) the cross-modal consistency prompt serves the establishment of information consistency of dual visual modalities; 2) the modality-specific prompt is inserted to adapt different input patterns; and 3) the missing-aware prompt is attached to compensate for the information vacancy caused by dynamic modalities-missing. In addition, we propose symmetric contrastive learning, which utilizes text modality as a bridge for fusion of dual vision modalities. Specifically, a paired antithetical text prompt is designed to generate binary text semantics, and triple-modal contrastive pretraining is offered to accomplish multimodal learning. Experiment results show that our proposed method achieves 73.83% I-AUROC and 93.05% P-AUROC with a total missing rate 0.7 for RGB and 3-D modalities (exceeding state-of-the-art methods 3.84% and 5.58%, respectively), and outperforms existing approaches to varying degrees under different missing types and rates.

24 December 2025 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
MGMeng Gao
Meng Gao
YMYunfeng Ma
Yunfeng Ma
SJShuai Jiang
Shuai Jiang
MLMin Liu
Min Liu
QSQi Su
Qi Su
YWYaonan Wang
Yaonan Wang
Few-shot semantic segmentation aims to reduce reliance on dense annotations, while enhancing generalization to unseen categories. However, most methods are constrained by static global prototypes, which fail to represent subtle defect details, resulting in pronounced support–query misalignment. To address this issue, we propose progressive adaptive network for defect-aware few-shot segmentation (PANDA), a few-shot segmentation framework that integrates representational modulation with semantic consistency constraints. Specifically, to capture subtle and scale-sensitive variations in defect patterns, we design anchored representational modulation (ARM), which overcomes the rigidity of static prototypes by dynamically adjusting representations. In addition, we develop hierarchical semantic coherence (HSC), which enforces consistency across representation hierarchies to suppress the accumulation of semantic drift as depth increases. Collectively, ARM and HSC mitigate support–query misalignment and stabilize representations in few-shot defect segmentation. PANDA achieves state-of-the-art performance on MetFS-18, with 55.1% and 56.3% mean intersection over union under the one-shot and five-shot settings. Moreover, PANDA has been integrated into a real-time industrial inspection platform, where it delivers accurate segmentation across diverse defect types, highlighting its robustness in practical application.