Hi, my name is Jun Dan.

I’m a 5th-year Ph.D. student at Zhejiang University.
Previously, I graduated with a bachelor’s degree in 2020 from the School of Microelectronics and Communication Engineering at Chongqing University.

Research Interests:

• Transfer Learning
• Face Perception and Understanding
• AIGC
• Data-Centric AI

My selected open-source projects:

(1) FaceChain ;

(2) TransFace ; TransFace model has reached over 13K+ downloads on the ModelScope platform, and has been applied in various facial AIGC projects, such as Alibaba Tongyi Wanxiang (通义万象写真馆), FaceChain, Fliggy (飞猪数字旅拍) and so on.

Publications

• TFGDA: Exploring Topology and Feature Alignment in Semi-supervised Graph Domain Adaptation through Robust Clustering. [PDF]
  Dan J, Liu W, Tan Y, et al. Accepted by NeurIPS 2024, Main Track.

• TopoFR: A Closer Look at Topology Alignment on Face Recognition. [PDF] [CODE] [机器之心] [CSDN] [CVer]
  Dan J, Liu Y, Deng J, et al. Accepted by NeurIPS 2024, Main Track.

• TransFace: Calibrating Transformer Training for Face Recognition from a Data-Centric Perspective. [PDF] [CODE] [ModelScope] [阿里云] [CVer] [CSDN]
  Dan J, Liu Y, Xie H, et al. Proceedings of the IEEE/CVF international conference on computer vision (ICCV). 2023: 20642-20653.

• HOGDA: Boosting Semi-supervised Graph Domain Adaptation via High-Order Structure-Guided Adaptive Feature Alignment. [PDF]
  Dan J, Liu W, Liu M, et al. Accepted by ACM Multimedia (ACM MM) 2024.

• PIRN: Phase Invariant Reconstruction Network for Infrared Image Super-Resolution. [PDF]
  Dan J, Jin T, Chi H, et al. Neurocomputing, 2024, 599: 128221.

• Similar Norm More Transferable: Rethinking Feature Norms Discrepancy in Adversarial Domain Adaptation. [PDF]
  Dan J, Liu M, Xie C, et al. Knowledge-Based Systems, 2024, 296: 111908.

• Trust-aware Conditional Adversarial Domain Adaptation with Feature Norm Alignment. [PDF]
  Dan J, Jin T, Chi H, et al. Neural Networks, 2023, 168: 518-530.

• HOMDA: High-Order Moment-Based Domain Alignment for unsupervised domain adaptation. [PDF]
  Dan J, Jin T, Chi H, et al. Knowledge-Based Systems, 2023, 261: 110205.

• Uncertainty-guided Joint Unbalanced Optimal Transport for Unsupervised Domain Adaptation. [PDF]
  Dan J, Jin T, Chi H, et al. Neural Computing and Applications, 2023, 35(7): 5351-5367.

• FaceChain-FACT: Face Adapter with Decoupled Training for Identity-preserved Personalization. [PDF] [CODE]
  Cheng Yu, Haoyu Xie, Lei Shang, Yang Liu, Jun Dan, et al. arXiv preprint arXiv:2410.12312, 2024.

• CM-UNet: Hybrid CNN-Mamba UNet for Remote Sensing Image Semantic Segmentation. [PDF] [CODE]
  Liu M, Dan J, Lu Z, et al. arXiv preprint arXiv:2405.10530, 2024.

News

• 🚀🚀🚀 TransFace is integrated in FaceChain as a key identity-preserved module to assist Stable Diffusion in generating human portraits with fine-grained facial details and diverse styles. In the newest FaceChain-FACT (Face Adapter with deCoupled Training) version, with only 1 photo and 10 seconds, you can generate personal portraits in different settings (multiple styles now supported!). (May 28th, 2024 UTC)
• You can quickly experience and invoke our TransFace model on the ModelScope.

The entire framework of FaceChain-FACT is shown in the figure below.

Awards & Honors

• National Scholarship, 2024.
• 3PEAK Corporate Scholarship, 2024.
• Five-Star Graduate Student of Zhejiang University, 2023 & 2024.
• Outstanding Graduate Student of Zhejiang University. 2021 & 2023 & 2024.
• Outstanding Graduate of Chongqing City, 2020. (1% students awarded)
• Outstanding Graduate of Chongqing University, 2020.
• National Encouragement Scholarship, 2017 & 2018 & 2019.
• Comprehensive Scholarship for Outstanding Students of Chongqing University, 2017 & 2018 & 2019 & 2020.