Skip to content
View beandkay's full-sized avatar
🏠
Working from home
🏠
Working from home

Highlights

  • Pro

Block or report beandkay

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
beandkay/README.md

Hi there 👋 My name is Binh, I obtained a PhD degree at Sungkyunkwan University, South Korea under supervisor Professor Joon-Sung Yang.

Research Interest

Visual Correspondence and its applications. e.g., Semantic Correspondence, Representation Learning, etc. Specifically, I am interested in effective model architecture for computer vision tasks or designing efficient methods for correspondence.
Effective Learning where I focus on various methods to effectively train Deep Neural Networks such as Dropout, Semi-supervised Learning, Un-normalized Neural Networks, etc.

Also, I'm always trying to study various fields not stated above for interdisciplinary research.

Education

  • Sungkyunkwan University, Seoul, Korea

    • M.S./Ph.D. Integrated Student in Electrical and Computer Engineering
    • Mar. 2019 - Aug. 2023
  • Ho Chi Minh University of Technology, Ho Chi Minh, Vietnam

    • B.S. in Computer Science
    • Aug. 2014 - Nov. 2018

Experience

  • Researcher (Yonsei University DATES Lab, Seoul, Korea)
    • Mar. 2019 - Present
    • Advisor: Prof. Joon-Sung Yang

Publications

International Journal

EUNNet: Efficient UN-normalized Convolution layer for stable training of Deep Residual Networks without Batch Normalization layer

Nguyen, Khanh-Binh and Choi, Jaehyuk and Yang, Joon-Sung
IEEE Access 2023
[Code] [Link]

Checkerboard Dropout: A Structured Dropout With Checkerboard Pattern for Convolutional Neural Networks

Nguyen, Khanh-Binh and Choi, Jaehyuk and Yang, Joon-Sung
IEEE Access 2022
[Code] [Link]

International Conference

Boosting Semi-Supervised Learning by bridging high and low-confidence predictions

Nguyen, Khanh-Binh, and Joon-Sung Yang
Workshop on representation learning with very limited images: the potential of self-, synthetic- and formula-supervision (ICCVW), 2023.
[Code] [Link]

VSCHH 2023: A Benchmark for the View Synthesis Challenge of Human Heads

Jang, Youngkyoon, Jiali Zheng, Jifei Song, Helisa Dhamo, Eduardo Pérez-Pellitero, Thomas Tanay, Matteo Maggioni, Nguyen, Khanh-Binh et al.
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
[Link]

Debiasing, calibrating, and improving Semi-supervised Learning performance via simple Ensemble Projector

Nguyen, Khanh-Binh
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024.
[Code] [Link]

(Oral, top 3%) SequenceMatch: Revisiting the design of weak-strong augmentations for Semi-supervised learning

Nguyen, Khanh-Binh
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024.
[Code] [Link]

Binh's github stats

Top Langs

Pinned Loading

  1. CheckerboardDropout CheckerboardDropout Public

    Code for Checkerboard Dropout paper

    Python

  2. EUNNet EUNNet Public

    Code for EUNNet paper

    Python

  3. EPASS EPASS Public

    Ensemble projector for better performance of contrastive-based Semi-supervised learning (CoMatch, SimMatch)

    Python

  4. SequenceMatch SequenceMatch Public

    Code for SequenceMatch (WACV 2024)

    Python 4