profile image

Jiacong Hu (胡佳聪)

Ph.D. @VIPA Lab

Welcome to my homepage👋! I am Jiacong Hu, a Ph.D. student in the Visual Intelligence and Pattern Analysis Laboratory (VIPA Lab) at Zhejiang University, advised by Professors Mingli Song and Zunlei Feng.

My current research focuses on trustworthy AI, AI model evaluation, model optimization, and efficient model training and reuse. I am particularly interested in building transparent and secure AI models that enhance model correctness, robustness, fairness, and transferability. I have also worked on projects combining AI with medical image. Beyond research, I enjoy photography📷 and badminton🏸.

News

Selected publication

  1. Model LEGO: Disassembling and assembling convolutional neural network

    Jiacong Hu, Jing Gao, Zunlei Feng, Lechao Cheng, Jie Lei, Hujun Bao, Mingli Song

    arXiv preprint arXiv:2203.134532024

  2. Improving Adversarial Robustness via Feature Pattern Consistency Constraint

    Jiacong Hu, Jingwen Ye, Zunlei Feng, Jiazhen Yang, Shunyu Liu, Xiaotian Yu, Lingxiang Jia, Mingli Song

    Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI2024

  3. Hundredfold Accelerating for Pathological Images Diagnosis and Prognosis through Self-reform Critical Region Focusing

    Xiaotian Yu, Haoming Luo, Jiacong Hu, Xiuming Zhang, Yuexuan Wang, Wenjie Liang, Yijun Bei, Mingli Song, Zunlei Feng

    Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI2024

  4. Model doctor: A simple gradient aggregation strategy for diagnosing and treating cnn classifiers

    Zunlei Feng, Jiacong Hu, Sai Wu, Xiaotian Yu, Jie Song, Mingli Song

    Proceedings of the AAAI Conference on Artificial Intelligence, AAAI2022

  5. A location constrained dual-branch network for reliable diagnosis of jaw tumors and cysts

    Jiacong Hu, Zunlei Feng, Yining Mao, Jie Lei, Dan Yu, Mingli Song

    Medical Image Computing and Computer Assisted Intervention, MICCAI2021

Projects

Model Evaluation

An online platform for comprehensive evaluation of deep learning model accuracy, robustness, fairness, and transferability.

June 20, 2024

project image