About

👋 Nice to meet you here!

I am a final-year Ph.D. candidate in the Electronic Information School, Wuhan University (WHU). My research pursues modeling multi-modal and multi-dimensional data and developing cutting-edge solutions to advance next-generation intelligent perception. It primarily unfolds on two complementary levels: (a) computational imaging fundamentals; (b) application-oriented projects. I have conducted research in the intersection of machine learning and remote sensing science, and have developed a series of methods for image synthesis, image restoration, and pixel-level classification. These methods have been preliminarily applied in aerospace, earth observations, smart cities, etc. I am devoted to developing innovative AI solutions for real-world challenges, and I hope to contribute to a better understanding of the world around us.
If you are interested in my research or would like to have a casual chat, please do not hesitate to reach me.

🔔 Currently, I am in the job market. I am excited to seek a postdoc position to continue advancing my research and applying my skills and expertise to new challenges. You can find my full CV here.

📢 By the way, I am delighted to assist undergraduate students in their academic and personal growth. Whether you need guidance on course selection, advice on research, or support navigating the challenges of university life, I am available to help. Please feel free to ask any questions you may have, and I will offer my support to the best of my ability.

Research

Multi-modal Fusion-based Hyperspectral Image SynthesisOngoing

Acquiring and processing hyperspectral data can be time-consuming and expensive, which causes a series of issues involving data scarcity, class skew, and target background restriction. It hinders the progress of large-scale AI-based studies and a range of applications.
To this end, we tend to raise a new paradigm of HSI synthesis, generating a vast amount of HSI with a rich diversity in various categories and scenes, closely resembling realistic data.

Robust Hyperspectral Image Restoration for Complex DegradationOngoing

Hyperspectral images are often affected by noise due to unstable factors in the complex imaging chain. This noise can significantly degrade the content and visual quality of the images, hindering their analysis and interpretation.
To alleviate these issues, we take advantage of the inherent characteristics of hyperspectral images and unique properties of hyperspectral degradation and incorporate both data-driven and model-driven strategies to propose a series of denoising and destriping methods.

Model-based Deep Learning Hyperspectral Image ClassificationProspective

A hyperspectral image is a three-dimensional data cube with high dimensionality, a strong correlation between adjacent bands, a highly nonlinear data structure, and few training samples. These characteristics make the hyperspectral image classification task challenging.
To tackle these challenges, we have endeavored to develop methods that improve classification accuracy, efficiency, and generalization ability.

Publications

This includes some of my recent publications. Check Google Scholar for a more complete list.

2024

  • Unmixing before Fusion: A Generalized Paradigm for Multi-Source-based Hyperspectral Image Synthesis
    URL | PDF | Poster | Slides
    Yang Yu*, Erting Pan*, Xinya Wang, Yuheng Wu, Xiaoguang Mei, and Jiayi Ma
    IEEE/CVF International Conference on Computer Vison and Pattern Recognition (CVPR), Seattle, WA, USA, Jun.2024.
  • From the Abundance Perspective: Multi-modal Fusion-based Hyperspectral Image Synthesis URL | PDF | CODE
    Erting Pan*, Yang Yu*, Xiaoguang Mei, Jun Huang, and Jiayi Ma
    Information Fusion

2023

  • Hyperspectral Image Destriping and Denoising from a Task Decomposition View URL | PDF | CODE
    Erting Pan, Ma Yong, Xiaoguang Mei, Fan Fan, and Jiayi Ma
    Pattern Recognition(PR), 2023.
  • Hyperspectral Image Denoising via Spectral Noise Distribution Bootstrap URL | PDF | CODE
    Erting Pan, Ma Yong, Xiaoguang Mei, Fan Fan, and Jiayi Ma
    Pattern Recognition(PR), 2023.
  • Progressive Hyperspectral Image Destriping with An Adaptive Frequencial Focus URL | PDF | CODE
    Erting Pan, Ma Yong, Xiaoguang Mei, Fan Fan, Jun Huang, and Jiayi Ma
    IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2023.
  • D2Net: Deep Denoising Network in Frequency Domain for Hyperspectral Image URL | PDF | CODE
    Erting Pan, Ma Yong, Xiaoguang Mei, Jun Huang, Fan Fan, and Jiayi Ma
    IEEE/CAA Journal of Automatica Sinica, 2023.

2022

  • SQAD: Spatial-Spectral Quasi-Attention Recurrent Network for Hyperspectral Image Denoising URL | PDF | CODE
    Erting Pan, Ma Yong, Xiaoguang Mei, Fan Fan, Jun Huang, and Jiayi Ma
    IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2022.

2021

  • Unsupervised Stacked Capsule Autoencoder for Hyperspectral Image Classification URL | PDF | Slides
    Erting Pan, Ma Yong, Xiaoguang Mei, Fan Fan, and Jiayi Ma
    IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, Canada, Jun.2021.
  • Hyperspectral Image Classification across Different Datasets: A Generalization to Unseen Categories URL | PDF | CODE
    Erting Pan, Ma Yong, Fan Fan, Xiaoguang Mei, and Jun Huang
    Remote Sensing, 2021.

2020

  • Spectral-Spatial Classification for Hyperspectral Image Based on a Single GRU URL | PDF | CODE
    Erting Pan, Xiaoguang Mei, Ma Yong, Quande Wang, and Jiayi Ma
    Neurocomputing, 2020.

2019

  • GRU with Spatial Prior for Hyperspectral Image Classification URL | PDF | Slides
    Erting Pan, Ma Yong, Xiaoguang Mei, Fan Fan, and Jiayi Ma
    IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Yokohama, Japan, Jul.2019.
  • Spectral-Spatial Attention Networks for Hyperspectral Image Classification URL | PDF | CODE
    Xiaoguang Mei, Erting Pan, Ma Yong, Xiaobing Dai, Jun Huang, Fan Fan, Qinglei Du, Hong Zheng, and Jiayi Ma
    Remote Sensing, 2019.
  • Spectral-Spatial Classification of Hyperspectral Image Based on a Joint Attention Network URL | PDF | Slides
    Erting Pan, Ma Yong, Xiaoguang Mei, Fan Fan, and Jiayi Ma
    IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Yokohama, Japan, Jul.2019.

Education

Ph.D. & M.Eng. in Signal and Information Processing
Wuhan University, Wuhan, China
2018 - present

B.Eng. in Electrical Engineering and its Automation
Northeast Normal University, Changchun, China
2014 - 2018

Service

Journal Reviewer

  • Information Fusion
  • IEEE Transactions on Image Processing (TIP)
  • IEEE/CAA Journal of Automatica Sinica (JAS)
  • IEEE Transactions on Geoscience and Remote Sensing (TGRS)
  • Neural Networks
  • Neurocomputing

Student Editor

Teaching Assistant

  • Engineering Stochastic Mathematics, Undergraduate course, WHU, 2021 Fall

Miscellaneous

I am a longtermist. Outside my research, I enjoy outdoor excercise such as jogging, riding, and hiking with friends. I used to be a member of Super Runner's Club in Changchun, and I have completed several half-marathon (2015'Harbin; 2017'Changchun; 2023'Wuhan) and full-marathon (2016'Dalian).