Mingjia Li

Master's student at Beijing Institute of Technology (BIT) with focus on scene understanding.

About Me

  • I am a first-year master's student at the Transfer Learning Group (BIT-DA) at Beijing Institute of Technology, advised by Prof. Shuang Li and Prof. Chi Harold Liu.

  • I received my bachelor's degree in Computer Science and Technology from BIT (2018-2022).

  • My research interests are in transfer learning and data-efficient scene understanding. My current research directions include domain adaptation for dense prediction tasks like semantic segmentation.

Publications

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

T-PAMI (IF: 24.31)

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

A novel one-stage adaptation framework that highlights the semantic concepts of individual pixel to promote learning of class-discriminative and class-balanced pixel embedding space across domains.

 

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

AAAI 2023 (Oral)

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

VBLC tackles the problem of domain adaptive semantic segmentation under adverse conditions, getting rid of reference images.