Lian Shijie (连仕杰)

Google Scholar  /  Github

Shijie Lian is a Ph.D. student at the School of Computer Science & Technology, Huazhong University of Science and Technology (HUST), under the supervision of Prof. Laurence T. Yang. He graduated from Hainan University with a B.S. degree in 2024. His research interests are computer vision and multimodal learning, especially scene understanding and image segmentation.

profile photo
Recent News

  • [07/2024] I have served as a reviewer for IEEE ISPA 2024 (CCF C).
  • [06/2024] I have served as a reviewer for IEEE TCSVT (IF: 8.3) and IEEE JOE (IF: 4.2).
  • [05/2024] One paper was accepted by ICML 2024.
  • [09/2023] I have served as a reviewer for IEEE ICPADS 2023 (CCF C).
  • [07/2023] One paper was accepted by ICCV 2023.
Publications ( * denotes contribution equally )

Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset},

Shijie Lian,  Ziyi Zhang,   Hua Li,   Wenjie Li,    Laurence Tianruo Yang,   Sam Kwong,   Runmin Cong

ICML, 2024      

Paper  |  Code  |  Dataset (USIS10K Dataset)  |  BibTex

We apply SAM to underwater salient instance segmentation (USIS), aiming to improve the segmentation accuracy in complex underwater scenes. We also present the largest existing USIS dataset, which has per-pixel labeling of 10,632 images.
WaterMask: Instance Segmentation for Underwater Imagery

Shijie Lian,   Hua Li,   Runmin Cong,   Suqi Li,   Wei Zhang,   Sam Kwong

ICCV, 2023      

Paper  |  Code  |  Dataset (UIIS Dataset)  |  BibTex

In this work, we present the first generalized underwater image instance segmentation dataset containing 4628 images with pixel-level annotations.
DSMISR: Differential Siamese Multi-scale Attention Network for Iris Image Super Resolution

Jin Hao,   Shijie Lian,   Suqi Li,   Hua Li

UIC, 2022

Paper  |  BibTex

In which we propose a super resolution neural network for Iris super resolution.
Honors & Awards
  • [09/2023] I was awarded the Chinese National Scholarship.