Bowen Cheng 程博文

Bowen is a fifth-year Ph.D. ABD in Electrical and Computer Engineering (ECE) at University of Illinois Urbana-Champaign (UIUC). His Ph.D. advisors are Prof. Alexander Schwing and Prof. Thomas Huang (2017-2020). Bowen is doing research in computer vision and machine learning. Before commencing his graduate studies, he received his B.S. in ECE at UIUC in 2017.

Bowen has interned at FAIR NYC (Facebook AI Research, New York City), FAIR MPK (Facebook AI Research, Menlo Park), Google Research (Los Angeles), Microsoft Research (Redmond) and Microsoft Research Asia (Beijing, China).

I’m actively looking for research scientist positions in the industry.

Research Interests

My current research focuses on computer vision and machine learning, in particular I have recently worked in:

  • Computer Vision
    • Recogntion: image classification and object detection
    • Grouping: panoptic, instance, and semantic segmentation
  • Machine Learning
    • Learning with limited label: self-supervised pre-training, semi-supervised segmentation, weakly-supervised object detection
    • Meta learning: neural architecture search

Please refer to my Google scholar for a full list of my publications.


  • [2021.12] Checkout our Mask2Former which outperforms specialized architectures on panoptic, instance and semantic segmentation with a single universal architecture for the first time. New SOTAs: 57.8 PQ on COCO panoptic segmentation, 50.1 AP on COCO instance segmentation and 57.7 mIoU on ADE20K semantic segmentation!
  • [2021.10] I received a NeurIPS 2021 Outstanding Reviewer Award.
  • [2021.09] MaskFormer accepted to NeurIPS 2021 as spotlight!
  • [2021.07] Checkout our MaskFormer which seamlessly unifies semantic- and instance-level segmentation tasks by treating semantic segmentation as a mask classification problem. Our MaskFormer acheives new SOTA on both semantic (55.6 mIoU on ADE20K) and panoptic segmentation (52.7 PQ on COCO).
  • [2021.06] I am co-organizing the LVIS Challenge at ICCV 2021, integrating Boundary IoU into the official challenge evaluation metric!
  • [2021.06] A TensorFlow2 re-implementation of Panoptic-DeepLab is released. Also check my PyTorch re-implementation here as well as in the official Detectron2.
  • [2021.04] Check out our Pointly-Supervised Instance Segmentation which shows instance segmentation models like Mask R-CNN can be trained with 10 points per instance and achieve 94%-98% of their fully-supervised performance on a variety of datasets.
  • [2021.03] Check out our Boundary IoU which introduces a new metric for image segmentation that focuses more on the boundary quality. Try our new Boundary AP and Boundary PQ metrics on your instance and panoptic segmentation models!
  • [2021.03] One paper accepted in CVPR 2021.


  • Mask2Former codebase based on Detectron2 [code]
  • MaskFormer codebase based on Detectron2 [code]
  • Pointly-supervised instance segmentation implementation in Detectron2 [code]
  • Panoptic-DeepLab implementation in Detectron2 [code]
  • DeepLab implementation in Detectron2 [code]
  • Panoptic-DeepLab implementation in PyToch from scratch [code]
  • HigherHRNet implementation in PyTorch [code]