Mingjia Li

Master's Student
Beijing Institute of Technology
mingjiali@bit.edu.cn

About Me

I am a Master’s student at Beijing Institute of Technology (BIT) with focus on scene understanding.

Research Interests

Computer Vision: diffusion models, semantic segmentation
Machine Learning: data-efficient learning, transfer learning

News

[Sep 2024] Our DUSA on diffusion-guided test-time adaptation is accepted to NeurIPS 2024.
[Nov 2023] SePiCo is selected as Highly Cited Paper! [screenshot]
[Jan 2023] Our SePiCo on cross-domain semantic segmentation is accepted to TPAMI (IF: 23.6).
[Nov 2022] Our VBLC on adverse-weather semantic segmentation is accepted to AAAI 2023 as Oral Presentation.

Publications

NeurIPS

Exploring Structured Semantic Priors Underlying Diffusion Score for Test-time Adaptation

Mingjia Li, Shuang Li, Tongrui Su, Longhui Yuan, Jian Liang, Wei Li

Annual Conference on Neural Information Processing Systems (NeurIPS), 2024

Project Page Paper Code BibTex

AAAI

VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions

Mingjia Li*, Binhui Xie*, Shuang Li, Chi Harold Liu, Xinjing Cheng

AAAI Conference on Artificial Intelligence (AAAI), 2023

Project Page Paper Code BibTex Oral Presentation

TPAMI

SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation

Binhui Xie, Shuang Li, Mingjia Li, Chi Harold Liu, Gao Huang, Guoren Wang

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023

Project Page Paper Code BibTex ESI Highly Cited Paper

About This Homepage & Project Pages

This is a Jekyll + Vue3 solution, source code can be found here.
Project page syntax supports for Kramdown can be found here

Powered by Jekyll and Minimal Light theme.