Lijia Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Lijia Yu has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Bo Liu
Southeast University, Nanjing, China and Purple Mountain Laboratories, Nanjing, China
2 shared publications - Jiuxin Cao
Southeast University, Nanjing, China and Purple Mountain Laboratories, Nanjing, China
2 shared publications - Biwei Cao
Hohai University, Nanjing, China
1 shared publication - Chang Liu
Southeast University, Nanjing, China
1 shared publication - Hanyu Luo
Southeast University, Nanjing, China
1 shared publication - Junyang Yang
School of Cyber Science and Engineering, Southeast University, Nanjing 211189, China
1 shared publication
Latest Publications
- 13 October 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 334
CorpusMark: LLM watermarking via public corpus probability priors
- 13 October 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 334
CorpusMark: LLM watermarking via public corpus probability priors
- 1 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (12) , 9297-9308
tGARD: Text-Guided Adversarial Reconstruction for Industrial Anomaly Detection
Industrial anomaly detection aims to identify and localize defective regions in images. Among various architectures, reconstruction-based methods have demonstrated exceptional performance. These methods reconstruct anomalous samples into normal ones and identify anomalies through a comparison between them. However, reconstruction process within these methods often focuses on PL similarity, overlooking the high-frequency consistency between the input and output, which constrains the model’s accuracy. This article proposes tGARD, a novel text-guided adversarial reconstruction method for anomaly detection. Specifically, we introduce feature aggregation module, using nonlocal block and dilated convolution to handle complex anomaly patterns. Subsequently, text-guided reconstruction module is meticulously designed to harness CLIP’s multimodal alignment capabilities, allowing for a semantically controllable reconstruction process. This control is achieved by incorporating dynamic text embeddings derived from the CLIP encoder within discriminator. Meanwhile, during reconstruction process, high-frequency details are preserved through a convolutional adversarial discriminator. Finally, category-aware loss weighting strategy is conceived to balance similarity and adversarial loss. Experiments demonstrate that our model achieves significant improvements in anomaly localization, surpassing all reconstruction-based models on MVTec-AD. It also establishes a new state-of-the-art on VisA dataset, outperforming all existing architectures.
- 1 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (12) , 9297-9308
tGARD: Text-Guided Adversarial Reconstruction for Industrial Anomaly Detection
Industrial anomaly detection aims to identify and localize defective regions in images. Among various architectures, reconstruction-based methods have demonstrated exceptional performance. These methods reconstruct anomalous samples into normal ones and identify anomalies through a comparison between them. However, reconstruction process within these methods often focuses on PL similarity, overlooking the high-frequency consistency between the input and output, which constrains the model’s accuracy. This article proposes tGARD, a novel text-guided adversarial reconstruction method for anomaly detection. Specifically, we introduce feature aggregation module, using nonlocal block and dilated convolution to handle complex anomaly patterns. Subsequently, text-guided reconstruction module is meticulously designed to harness CLIP’s multimodal alignment capabilities, allowing for a semantically controllable reconstruction process. This control is achieved by incorporating dynamic text embeddings derived from the CLIP encoder within discriminator. Meanwhile, during reconstruction process, high-frequency details are preserved through a convolutional adversarial discriminator. Finally, category-aware loss weighting strategy is conceived to balance similarity and adversarial loss. Experiments demonstrate that our model achieves significant improvements in anomaly localization, surpassing all reconstruction-based models on MVTec-AD. It also establishes a new state-of-the-art on VisA dataset, outperforming all existing architectures.