Khoi Nguyen

Khoi Nguyen

AI Research Scientist

VinAI Research

Biography

Khoi Nguyen is a PhD in Computer Science graduating from Oregon State University. His research interests include computer vision and machine learning. His primary research includes 2D/3D understanding, encompassing areas such as reconstruction, detection, and segmentation. In addition, Khoi is actively involved in advancing 2D/3D Generation techniques, leveraging cutting-edge technologies like Diffusion Models and Neural Radiance Fields (NeRFs). He also explores the realms of Few-shot Learning and Vision-Language Models, contributing to push the boundaries of knowledge and innovation.

Interests

  • 2D/3D Understanding including Detection, Segmentation
  • 2D/3D Generation including Diffusion Models, Neural Randiance Fields (NeRFs)
  • Few-shot Learning and Vision-Language Models

Education

  • PhD in Computer Science, 2021

    Oregon State University

  • MSc in Computer Science, 2017

    Oregon State University

  • BSc in Computer Science, 2014

    Ho Chi Minh City University of Technology (Bach Khoa University)

Recent News

All news»

[10/23] One paper accepted to WACV 2024 in Open-vocab Object Detection. Congrats to the first authors Chau Pham and Truong Vu for their first paper!

[09/23] One paper accepted to NeurIPS 2023. Congrats to the first authors Quang Nguyen and Truong Vu for their first paper!

[07/23] One paper accepted to ICCV 2023. Congrats to the first author Tuan Ngo for his third paper!

[03/23] One paper accepted to CVPR 2023. Cheers!

[01/23] Our paper accepted to WACV 2023 is awarded as the Best Paper - Honorable Mention!

Publications

LP-OVOD: Open-Vocabulary Object Detection by Linear Probing

Chau Pham*, Truong Vu*, Khoi Nguyen, in WACV 2024
PDF Code
LP-OVOD: Open-Vocabulary Object Detection by Linear Probing

Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentation

Quang Nguyen*, Truong Vu*, Anh Tran, Khoi Nguyen, in NeurIPS 2023
PDF Code
Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentation

GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo Labelers

Tuan Ngo, Binh-Son Hua, Khoi Nguyen, in ICCV 2023
PDF Code
GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo Labelers

ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution,

Tuan Ngo, Binh-Son Hua, Khoi Nguyen, in CVPR 2023
PDF Code
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution,

PSENet: Progressive Self-Enhancement Network for Unsupervised Extreme-Light Image Enhancement

Hue Nguyen, Diep Tran, Khoi Nguyen, Rang Nguyen, in WACV 2023 (Best Paper - Honorable Mention Award!!!)
PDF Code
PSENet: Progressive Self-Enhancement Network for Unsupervised Extreme-Light Image Enhancement

Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments

Khoi D. Nguyen, Quoc-Huy Tran, Khoi Nguyen, Binh-Son Hua, Rang Nguyen, in ECCV 2022
PDF Code
Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments

Few Shot Counting and Detection

Thanh Nguyen*, Chau Pham*, Khoi Nguyen, Minh Hoai, in ECCV 2022
PDF Code
Few Shot Counting and Detection

Geodesic-Former: a Geodesic-Guided Few-shot 3D Point Cloud Instance Segmenter

Tuan Ngo, Khoi Nguyen, in ECCV 2022
PDF Code
Geodesic-Former: a Geodesic-Guided Few-shot 3D Point Cloud Instance Segmenter

iFS-RCNN: An Incremental Few-shot Instance Segmenter

Khoi Nguyen, Sinisa Todorovic, in CVPR 2022
PDF Code Poster
iFS-RCNN: An Incremental Few-shot Instance Segmenter

POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples

Duong H. Le*, Khoi D. Nguyen*, Khoi Nguyen, Quoc-Huy Tran, Rang Nguyen, Binh-Son Hua, in NeurIPS 2021
PDF Code
POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples

A Weakly Supervised Amodal Segmenter with Boundary Uncertainty Estimation

Khoi Nguyen, Sinisa Todorovic, in ICCV 2021
PDF Code Poster
A Weakly Supervised Amodal Segmenter with Boundary Uncertainty Estimation

FAPIS: A Few-shot Anchor-free Part-based Instance Segmenter

Khoi Nguyen, Sinisa Todorovic, in CVPR 2021
PDF Code Poster
FAPIS: A Few-shot Anchor-free Part-based Instance Segmenter

A Self-supervised GAN for Unsupervised Few-shot Object Recognition

Khoi Nguyen, Sinisa Todorovic, in ICPR 2020
PDF
A Self-supervised GAN for Unsupervised Few-shot Object Recognition

Feature Weighting and Boosting for Few-Shot Segmentation

Khoi Nguyen, Sinisa Todorovic, in ICCV 2019
PDF Code Poster
Feature Weighting and Boosting for Few-Shot Segmentation

Employment

 
 
 
 
 

Research Scientist

VinAI Research

Jul 2021 – Present Hanoi, Vietnam
Computer Vision and Machine Learning Research and Mentoring
 
 
 
 
 

Research Intern

AIBee US Corp.

Jun 2019 – Sep 2019 Palo Alto, California
  • Topic: Multi-person Tracking by Segmentation in Surveillance Camera
  • Mentors: Dr. Chunhui Gu, Dr. Sinisa Todorovic, Dr. Silvio Savarese
 
 
 
 
 

Research Intern

Verisk Analytics

Jun 2018 – Sep 2018 Jersey City, New Jersey
  • Topic: Apply Graph Neural Network to image document analysis for extracting semistructured information (W2 Form)
  • Mentor: Dr. Maneesh Singh

Services and Awards

Services

  • Conference Reviewer:

    • CVPR 2021, 2022, 2023
    • ECCV 2020, 2022
    • ICCV 2021, 2023
    • NeurIPS 2022, 2023
    • ICLR 2022, 2023

  • Journal Reviewer:

    • TPAMI
    • TIP

Awards

  • Best Paper - Honorable Mention Award, WACV 2023
  • Outstanding Reviewer for ECCV 2020
  • VietNam Education Foundation (VEF) Fellowship (Cohort 2015)

Recent Posts

ProbML

Context: Welcome to the reading guide for “Probabilistic Machine Learning” by Kevin Murphy. The first version of this book, published in 2012 (probml.github.io/pml-book/book0.html) gained widespread recognition in the Machine Learning community and was often referred to as the “Bible of Machine Learning.
Jul 23, 2023 2 min read
ProbML

PhD Guidance

This is the PhD guidance from my own experience including: (1) Defining your goals (2) How to choose a university and a professor (3) The needed mindset (4) The worth noting things in research (5) Career paths after graduation (6) Attitude after graduation It is specially written for Vietnamese student, but you can use Google Translate for your convinence.
Nov 21, 2021 1 min read

Overview of Machine Learning

This is my first post on Machine Learning, Deep Learning and Computer Vision series in Medium. I am currently a Ph.D. Student in Computer Science with research interests are Computer Vision and Machine Learning.
Aug 16, 2020 5 min read

How to use Google Scholar for advancing your research

One of the most powerful and common tools for your research is Google Scholar. It contains many useful features that are necessary for your research. If you can make use of it, you do not need any proprietary software.
Aug 16, 2020 4 min read

Introduction to Machine Learning

This is the overview of basic and important machine learning models, methods and concepts and theories. I acknowledge all information and knowledge including images, data… I have taken from those two courses: https://www.
Aug 16, 2020 1 min read