Xi Jiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Xi Jiang has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
- Feng Zheng
Southern University of Science and Technology
5 shared publications - Chengjie Wang
YouTu Lab, Tencent, Shanghai, China
4 shared publications - Bin-Bin Gao
Tencent Youtu Lab, Shenzhen, China
2 shared publications - Feng Zheng
Southern University of Science and Technology
2 shared publications - Guo-Jun Qi
Research Center for Industries of the Future and the School of Engineering, Westlake University, Hangzhou, China
2 shared publications - Heng Huang
Department of Computer Science, University of Maryland, College Park, College Park, MD, USA
2 shared publications
Latest Publications
- 15 October 2026
- Published by Elsevier in Pattern Recognition
- Vol. 183
iCAS: An in-context anomaly segmentation framework for industrial visual inspection
- 15 October 2026
- Published by Elsevier in Pattern Recognition
- Vol. 183
iCAS: An in-context anomaly segmentation framework for industrial visual inspection
- Open Access
- 28 August 2026
- Published by MDPI AG in Preprints.org
A Survey of Recent Advances in Industrial Anomaly Detection: From Normal-Only Training to Foundation-Model Priors
Industrial anomaly detection supports automated quality inspection. Traditionally, each product has required its own detector, trained on images without defects and evaluated on benchmarks with fixed classes. Recent studies use vision encoders pretrained on web data, multimodal large language models, expert mixtures, and generative models to relax this setup. They transfer visual features, add reasoning through language, share models across categories and modalities, or generate abnormal training data. Existing taxonomies centered on reconstruction, embedding, distillation, and memory do not describe these developments well. We therefore organize the literature published over the past three years according to five sources of information that replace training on normal samples for each category, namely visual, reasoning, geometric and multimodal, universal, and synthesis priors. Reported results show progress on curated benchmarks, but evidence remains limited under domain shift, protocols for open world settings, and operating points with low false positive rates. We also analyze recent benchmarks and recurring deployment bottlenecks. Industrial video grounded in physical dynamics provides an emerging direction beyond inspection of single frames. The evidence points to a change in research focus, although current methods do not yet provide a general replacement for separate training on normal data for each product in deployed inspection.
- 28 August 2026
- Published by MDPI AG in Preprints.org
Open AccessA Survey of Recent Advances in Industrial Anomaly Detection: From Normal-Only Training to Foundation-Model Priors
Industrial anomaly detection supports automated quality inspection. Traditionally, each product has required its own detector, trained on images without defects and evaluated on benchmarks with fixed classes. Recent studies use vision encoders pretrained on web data, multimodal large language models, expert mixtures, and generative models to relax this setup. They transfer visual features, add reasoning through language, share models across categories and modalities, or generate abnormal training data. Existing taxonomies centered on reconstruction, embedding, distillation, and memory do not describe these developments well. We therefore organize the literature published over the past three years according to five sources of information that replace training on normal samples for each category, namely visual, reasoning, geometric and multimodal, universal, and synthesis priors. Reported results show progress on curated benchmarks, but evidence remains limited under domain shift, protocols for open world settings, and operating points with low false positive rates. We also analyze recent benchmarks and recurring deployment bottlenecks. Industrial video grounded in physical dynamics provides an emerging direction beyond inspection of single frames. The evidence points to a change in research focus, although current methods do not yet provide a general replacement for separate training on normal data for each product in deployed inspection.
- Open Access
UniPCB: A Unified Vision-Language Benchmark for Open-Ended PCB Quality Inspection
Multimodal Large Language Models (MLLMs) show promise for general industrial quality inspection, but fall short in complex scenarios, such as Printed Circuit Board (PCB) inspection. PCB inspection poses unique challenges due to densely packed components, complex wiring structures, and subtle defect patterns that require specialized domain expertise. However, a high-quality, unified vision-language benchmark for quantitatively evaluating MLLMs across PCB inspection tasks remains absent, stemming not only from limited data availability but also from fragmented datasets and inconsistent standardization. To fill this gap, we propose UniPCB, the first unified vision-language benchmark for open-ended PCB quality inspection. UniPCB is built via a systematic pipeline that curates and standardizes data from disparate sources across three annotated scenarios. Furthermore, we introduce PCB-GPT, an MLLM trained on a new instruction dataset generated by this pipeline, utilizing a novel progressive curriculum that mimics the learning process of human experts. Evaluations on the UniPCB benchmark show that while existing MLLMs falter on domain-specific tasks, PCB-GPT establishes a new baseline. Notably, it more than doubles the performance on fine-grained defect localization compared to the strongest competitors, with significant advantages in localization and analysis. We will release the instruction data, benchmark, and model to facilitate future research.
Open AccessUniPCB: A Unified Vision-Language Benchmark for Open-Ended PCB Quality Inspection
Multimodal Large Language Models (MLLMs) show promise for general industrial quality inspection, but fall short in complex scenarios, such as Printed Circuit Board (PCB) inspection. PCB inspection poses unique challenges due to densely packed components, complex wiring structures, and subtle defect patterns that require specialized domain expertise. However, a high-quality, unified vision-language benchmark for quantitatively evaluating MLLMs across PCB inspection tasks remains absent, stemming not only from limited data availability but also from fragmented datasets and inconsistent standardization. To fill this gap, we propose UniPCB, the first unified vision-language benchmark for open-ended PCB quality inspection. UniPCB is built via a systematic pipeline that curates and standardizes data from disparate sources across three annotated scenarios. Furthermore, we introduce PCB-GPT, an MLLM trained on a new instruction dataset generated by this pipeline, utilizing a novel progressive curriculum that mimics the learning process of human experts. Evaluations on the UniPCB benchmark show that while existing MLLMs falter on domain-specific tasks, PCB-GPT establishes a new baseline. Notably, it more than doubles the performance on fine-grained defect localization compared to the strongest competitors, with significant advantages in localization and analysis. We will release the instruction data, benchmark, and model to facilitate future research.
- 5 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (2) , 2300-2311
Tuning-Free Adaptive Style Incorporation for Structure-Consistent Text-Driven Style Transfer
Text-driven style transfer methods leveraging diffusion models have shown impressive creativity, yet they still face challenges in maintaining consistent structure and content preservation. Existing methods often directly concatenate the content and style prompts for a prompt-level style injection. However, this coarse-grained style injection strategy inevitably leads to structural deviations in the stylized images. This poses a significant obstacle for professional artists and creators seeking precise artistic editing. In this work, we strive to attain a harmonious balance between content preservation and style transformation. We propose Adaptive Style Incorporation (ASI), to achieve fine-grained feature-level style incorporation. It consists of the Siamese Cross-Attention (SiCA) to decouple the single-track cross-attention to a dual-track structure to obtain separate content and style features, and the Adaptive Content-Style Blending (AdaBlending) module to couple the content and style information from a structure-consistent manner. Experimentally, our method exhibits much better performance in both structure preservation and stylized effects.
- 5 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (2) , 2300-2311
Tuning-Free Adaptive Style Incorporation for Structure-Consistent Text-Driven Style Transfer
Text-driven style transfer methods leveraging diffusion models have shown impressive creativity, yet they still face challenges in maintaining consistent structure and content preservation. Existing methods often directly concatenate the content and style prompts for a prompt-level style injection. However, this coarse-grained style injection strategy inevitably leads to structural deviations in the stylized images. This poses a significant obstacle for professional artists and creators seeking precise artistic editing. In this work, we strive to attain a harmonious balance between content preservation and style transformation. We propose Adaptive Style Incorporation (ASI), to achieve fine-grained feature-level style incorporation. It consists of the Siamese Cross-Attention (SiCA) to decouple the single-track cross-attention to a dual-track structure to obtain separate content and style features, and the Adaptive Content-Style Blending (AdaBlending) module to couple the content and style information from a structure-consistent manner. Experimentally, our method exhibits much better performance in both structure preservation and stylized effects.
- 18 July 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (10) , 7293-7311
Towards Balanced Representation Learning with Semantic Anchor Regularization
- 18 July 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (10) , 7293-7311
Towards Balanced Representation Learning with Semantic Anchor Regularization
- 20 December 2024
- Published by Elsevier in Pattern Recognition
- Vol. 161
SoftPatch+: Fully unsupervised anomaly classification and segmentation
- 20 December 2024
- Published by Elsevier in Pattern Recognition
- Vol. 161
SoftPatch+: Fully unsupervised anomaly classification and segmentation
- Open Access
SoftPatch: Unsupervised Anomaly Detection with Noisy Data
Although mainstream unsupervised anomaly detection (AD) algorithms perform well in academic datasets, their performance is limited in practical application due to the ideal experimental setting of clean training data. Training with noisy data is an inevitable problem in real-world anomaly detection but is seldom discussed. This paper considers label-level noise in image sensory anomaly detection for the first time. To solve this problem, we proposed a memory-based unsupervised AD method, SoftPatch, which efficiently denoises the data at the patch level. Noise discriminators are utilized to generate outlier scores for patch-level noise elimination before coreset construction. The scores are then stored in the memory bank to soften the anomaly detection boundary. Compared with existing methods, SoftPatch maintains a strong modeling ability of normal data and alleviates the overconfidence problem in coreset. Comprehensive experiments in various noise scenes demonstrate that SoftPatch outperforms the state-of-the-art AD methods on the MVTecAD and BTAD benchmarks and is comparable to those methods under the setting without noise.
Open AccessSoftPatch: Unsupervised Anomaly Detection with Noisy Data
Although mainstream unsupervised anomaly detection (AD) algorithms perform well in academic datasets, their performance is limited in practical application due to the ideal experimental setting of clean training data. Training with noisy data is an inevitable problem in real-world anomaly detection but is seldom discussed. This paper considers label-level noise in image sensory anomaly detection for the first time. To solve this problem, we proposed a memory-based unsupervised AD method, SoftPatch, which efficiently denoises the data at the patch level. Noise discriminators are utilized to generate outlier scores for patch-level noise elimination before coreset construction. The scores are then stored in the memory bank to soften the anomaly detection boundary. Compared with existing methods, SoftPatch maintains a strong modeling ability of normal data and alleviates the overconfidence problem in coreset. Comprehensive experiments in various noise scenes demonstrate that SoftPatch outperforms the state-of-the-art AD methods on the MVTecAD and BTAD benchmarks and is comparable to those methods under the setting without noise.
- Open Access
Toward Multi-class Anomaly Detection: Exploring Class-aware Unified Model against Inter-class Interference
In the context of high usability in single-class anomaly detection models, recent academic research has become concerned about the more complex multi-class anomaly detection. Although several papers have designed unified models for this task, they often overlook the utility of class labels, a potent tool for mitigating inter-class interference. To address this issue, we introduce a Multi-class Implicit Neural representation Transformer for unified Anomaly Detection (MINT-AD), which leverages the fine-grained category information in the training stage. By learning the multi-class distributions, the model generates class-aware query embeddings for the transformer decoder, mitigating inter-class interference within the reconstruction model. Utilizing such an implicit neural representation network, MINT-AD can project category and position information into a feature embedding space, further supervised by classification and prior probability loss functions. Experimental results on multiple datasets demonstrate that MINT-AD outperforms existing unified training models.
Open AccessToward Multi-class Anomaly Detection: Exploring Class-aware Unified Model against Inter-class Interference
In the context of high usability in single-class anomaly detection models, recent academic research has become concerned about the more complex multi-class anomaly detection. Although several papers have designed unified models for this task, they often overlook the utility of class labels, a potent tool for mitigating inter-class interference. To address this issue, we introduce a Multi-class Implicit Neural representation Transformer for unified Anomaly Detection (MINT-AD), which leverages the fine-grained category information in the training stage. By learning the multi-class distributions, the model generates class-aware query embeddings for the transformer decoder, mitigating inter-class interference within the reconstruction model. Utilizing such an implicit neural representation network, MINT-AD can project category and position information into a feature embedding space, further supervised by classification and prior probability loss functions. Experimental results on multiple datasets demonstrate that MINT-AD outperforms existing unified training models.
- Open Access
A Bayesian Federated Learning Framework with Online Laplace Approximation
Federated learning (FL) allows multiple clients to collaboratively learn a globally shared model through cycles of model aggregation and local model training, without the need to share data. Most existing FL methods train local models separately on different clients, and then simply average their parameters to obtain a centralized model on the server side. However, these approaches generally suffer from large aggregation errors and severe local forgetting, which are particularly bad in heterogeneous data settings. To tackle these issues, in this paper, we propose a novel FL framework that uses online Laplace approximation to approximate posteriors on both the client and server side. On the server side, a multivariate Gaussian product mechanism is employed to construct and maximize a global posterior, largely reducing the aggregation errors induced by large discrepancies between local models. On the client side, a prior loss that uses the global posterior probabilistic parameters delivered from the server is designed to guide the local training. Binding such learning constraints from other clients enables our method to mitigate local forgetting. Finally, we achieve state-of-the-art results on several benchmarks, clearly demonstrating the advantages of the proposed method.
Open AccessA Bayesian Federated Learning Framework with Online Laplace Approximation
Federated learning (FL) allows multiple clients to collaboratively learn a globally shared model through cycles of model aggregation and local model training, without the need to share data. Most existing FL methods train local models separately on different clients, and then simply average their parameters to obtain a centralized model on the server side. However, these approaches generally suffer from large aggregation errors and severe local forgetting, which are particularly bad in heterogeneous data settings. To tackle these issues, in this paper, we propose a novel FL framework that uses online Laplace approximation to approximate posteriors on both the client and server side. On the server side, a multivariate Gaussian product mechanism is employed to construct and maximize a global posterior, largely reducing the aggregation errors induced by large discrepancies between local models. On the client side, a prior loss that uses the global posterior probabilistic parameters delivered from the server is designed to guide the local training. Binding such learning constraints from other clients enables our method to mitigate local forgetting. Finally, we achieve state-of-the-art results on several benchmarks, clearly demonstrating the advantages of the proposed method.
- 9 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (1) , 1-16
A Bayesian Federated Learning Framework With Online Laplace Approximation
Federated learning (FL) allows multiple clients to collaboratively learn a globally shared model through cycles of model aggregation and local model training, without the need to share data. Most existing FL methods train local models separately on different clients, and then simply average their parameters to obtain a centralized model on the server side. However, these approaches generally suffer from large aggregation errors and severe local forgetting, which are particularly bad in heterogeneous data settings. To tackle these issues, in this paper, we propose a novel FL framework that uses online Laplace approximation to approximate posteriors on both the client and server side. On the server side, a multivariate Gaussian product mechanism is employed to construct and maximize a global posterior, largely reducing the aggregation errors induced by large discrepancies between local models. On the client side, a prior loss that uses the global posterior probabilistic parameters delivered from the server is designed to guide the local training. Binding such learning constraints from other clients enables our method to mitigate local forgetting. Finally, we achieve state-of-the-art results on several benchmarks, clearly demonstrating the advantages of the proposed method.
- 9 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (1) , 1-16
A Bayesian Federated Learning Framework With Online Laplace Approximation
Federated learning (FL) allows multiple clients to collaboratively learn a globally shared model through cycles of model aggregation and local model training, without the need to share data. Most existing FL methods train local models separately on different clients, and then simply average their parameters to obtain a centralized model on the server side. However, these approaches generally suffer from large aggregation errors and severe local forgetting, which are particularly bad in heterogeneous data settings. To tackle these issues, in this paper, we propose a novel FL framework that uses online Laplace approximation to approximate posteriors on both the client and server side. On the server side, a multivariate Gaussian product mechanism is employed to construct and maximize a global posterior, largely reducing the aggregation errors induced by large discrepancies between local models. On the client side, a prior loss that uses the global posterior probabilistic parameters delivered from the server is designed to guide the local training. Binding such learning constraints from other clients enables our method to mitigate local forgetting. Finally, we achieve state-of-the-art results on several benchmarks, clearly demonstrating the advantages of the proposed method.