Huaxi Huang

Huaxi Huang

Researcher

Shanghai AI Laboratory

Biography

Dr. Huaxi Huang is currently a researcher at Shanghai AI Laboratory. He previously worked as a Computer Vision and Machine Learning Engineer at Lumachain. He also served as a CERC Research Fellow at CSIRO and the Sydney AI Centre. Dr. Huang was awarded his Ph.D. from the Faculty of Engineering and Information Technology at the University of Technology Sydney in 2022. Between 2010 and 2017, he obtained his B.Eng. and M.Eng. degrees from the School of Computer Software Engineering and the School of Computer Science and Technology at Tianjin University. His research interests include multimedia data analysis, computer vision, and trustworthy machine learning.

Interests
  • Trustworthy Machine Learning
  • Multimedia Data Analysis
  • Computer Vision
  • MLLM & LLM
Education
  • Ph.D. in Data Analytics, 2022

    University of Technology Sydney (UTS)

  • M.Eng. in Computer Science, 2017

    Tianjin University (TJU)

  • B.Eng. in Computer Software Engineering, 2014

    Tianjin University (TJU)

Recent Publications

Quickly discover relevant content by filtering publications.
(2023). Unleashing the Potential of Regularization Strategies in Learning with Noisy Labels. In arXiv 2023.

(2023). PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels. In ICCV 2023.

(2023). Masked Cross-image Encoding For Few-shot Segmentation. In ICME 2023 (Oral).

(2021). PTN: A Poisson Transfer Network for Semi-supervised Few-shot Learning. In AAAI 2021 (Oral & Poster).

PDF Cite

(2021). TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samples. In TCSVT 2021.

Cite DOI

(2020). Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification. In TMM 2020.

Cite DOI

(2019). Compare More Nuanced: Pairwise Alignment Bilinear Network for Few-Shot Fine-Grained Learning. In ICME 2019 (Oral).

Cite DOI

(2018). Railway Infrastructure Defects Recognition using Fine-grained Deep Convolutional Neural Networks. In DICTA 2018 (Oral).

Cite DOI

(2016). Multi-view Representative and Informative Induced Active Learning. In PRICAI 2016 (Oral).

Cite DOI