Name：Lu Yu
Title：Associate Professor
Type of tutor：Doctoral Supervisor，Master’s Supervisor
Email：luyu@email.tjut.edu.cn
Address：1-305
I am currently an associate professor at Tianjin University of Technology, Tianjin, China. Before that, I was a postdoctoral researcher at Heriot-Watt University in Edinburgh, UK. I received my Ph.D. in Computer Science from the Autonomous University of Barcelona in Barcelona, Spain, in 2019, and my master’s degree from Northwestern Polytechnical University in Xi’an, China, in 2015. My research interests include continual learning, model robustness, multimodal learning.
Computer Vision and Machine Learning
1.Principal Investigator, General Program of the National Natural Science Foundation of China
2.Principal Investigator, Young Scientists Fund of the National Natural Science Foundation of China
3.Principal Investigator, Postdoctoral Research Project funded by the Engineering and Physical Sciences Research Council (EPSRC), UK
[1] Lu Yu, Haiyang Zhang, Changsheng Xu. "Complementary Text-Guided Attention for Zero-Shot Adversarial Robustness. " In TPAMI 2026. (JCR Q1)
[2] Jifei Luo, Wenzheng Wu, Hantao Yao, Lu Yu, Changsheng Xu. "Locality Preserving Markovian Transition for Instance Retrieval." In ICML 2025. (CCF-A Conference)
[3] Zhe Tao, Lu Yu, Hantao Yao, Changsheng Xu. "Leveraging Multiple Deep Experts for Online Class-incremental Learning." In ICME 2025. (CCF-B Conference)
[4] Lu Yu, Haoyu Han, Zhe Tao, Hantao Yao, Changsheng Xu. "Language Guided Concept Bottleneck Models for Interpretable Continual Learning." In CVPR 2025. (CCF-A Conference)
[5] Lu Yu, Haiyang Zhang, and Changsheng Xu. "Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models." In NeurIPS 2024. (CCF-A Conference)
[6] Zhe Tao, Lu Yu, Hantao Yao, Shucheng Huang, and Changsheng Xu. "Class incremental learning for light-weighted networks." IEEE Transactions on Circuits and Systems for Video Technology (2024). (JCR Q1)
[7] Hantao Yao, Jifei Luo, Lu Yu, and Changsheng Xu. "Camera-Incremental Object Re-Identification With Identity Knowledge Evolution." IEEE Transactions on Multimedia (2024). (JCR Q1)
[8] Jiang-Tian Zhai, Xialei Liu, Lu Yu, and Ming-Ming Cheng. "Fine-grained knowledge selection and restoration for non-exemplar class incremental learning." In AAAI 2024. (CCF-A Conference)
[9] Hantao Yao, Lu Yu, Changsheng Xu. "Few-shot Incremental Learning with Textual Knowledge Embedding by Visual-language Model". International Journal of Software & Informatics, 2024.
[10] Yu Lu, Malvina Nikandrou, Jiali Jin, and Verena Reiser. "Quality-agnostic Image Captioning to Safely Assist People with Vision Impairment." In IJCAI 2023. (CCF-B Conference)
[11] Yu Lu, and Verena Rieser. "Adversarial Textual Robustness on Visual Dialog." Findings of the Association for Computational Linguistics: ACL 2023.
[12] Yu Lu, Xialei Liu, and Joost Van de Weijer. "Self-training for class-incremental semantic segmentation." IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2022. (JCR Q1)
[13] Gomez-Villa, Alex, Bartlomiej Twardowski, Lu Yu, Andrew D. Bagdanov, and Joost Van de Weijer. "Continually learning self-supervised representations with projected functional regularization." In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2022. (Best Paper of the "Continual Learning" Forum at CVPR)
[14] Yaxing Wang, Joost Van de Weijer, Lu Yu* and SHANGLING JUI. "Distilling GANs with Style-Mixed Triplets for X2I Translation with Limited Data." International Conference on Learning Representations (ICLR), 2021. (CCF-A Conference)
[15] Yaxing Wang, Lu Yu, and Joost van de Weijer. "Deepi2i: Enabling deep hierarchical image-to-image translation by transferring from gans." In NeurIPS 2020. (CCF-A Conference)
[16] Lu Yu, Bartlomiej Twardowski, Xialei Liu, Luis Herranz, Kai Wang, Yongmei Cheng, Shangling Jui, and Joost van de Weijer. "Semantic drift compensation for class-incremental learning." In CVPR 2020. (CCF-A Conference)
[17] Yaxing Wang, Yu Lu, and Joost van de Weijer. "Deepi2i: Enabling deep hierarchical image-to-image translation by transferring from gans." In NeurIPS 2020. (CCF-A Conference)
[18] Lu Yu, Vacit Oguz Yazici, Xialei Liu, Joost van de Weijer, Yongmei Cheng, and Arnau Ramisa. "Learning metrics from teachers: Compact networks for image embedding." In CVPR 2019. (CCF-A Conference)
Digital Logic (Undergraduate)
Academic English (Undergraduate)
Academic Writing for Research (Graduate)
2024 Distinguished Award for Excellence in Teaching and Mentorship
2024.01 Third Prize, 2nd Guangdong–Hong Kong–Macao Greater Bay Area (Huangpu) International Algorithm Case Competition
2023.08 Best Poster Paper Award, ChinaMM
2022.06 Best Paper Award, Continual Learning Workshop, CVPR
2015.09 Chinese Government Scholarship, China Scholarship Council
