Jeremy Yang

Xin (Jeremy) Yang

Hello! I am a 4th year PhD candidate at the National University of Singapore (ECE), working under the guidance of Prof. Robby Tan and Prof. XinChao Wang.

Prior to this, I earned my Master's degree in Software Engineering from The University of Auckland, where I also completed my Bachelor's degree, double majoring in Software Engineering and Finance.

I am also appointed as a reviewer of international AI journals and conferences like CVPR, ICCV, ECCV, AAAI, NeurIPS.

Email / Google Scholar

News

Nov 2024: Our work "ERF: A Benchmark Dataset for Robust Semantic Segmentation under Extreme Rainfall Conditions" is accepted by AAAI 2025!
Nov 2024: Our work "Semantic Segmentation on Raindrop Degraded Images Using Two-Stage Dual Teacher-Student Learning" is accepted by AAAI 2025!
Sep 2024: Our work "End-to-End Video Semantic Segmentation in Adverse Weather using Fusion Blocks and Temporal-Spatial Teacher-Student Learning" is accepted by NeurIPS 2024!
Dec 2023: Our work "Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention" is accepted by AAAI 2024!
Sep 2022: Our work "Object Detection in Foggy Scenes by Embedding Depth and Reconstruction into Domain Adaptation" is accepted by ACCV 2022!
Jan 2021: Starting my PhD in Computer Vision.

Research

My research focuses on unsupervised and semi-supervised high-level computer vision tasks, especially under adverse, challenging, or unlabeled conditions. I am keen to extend my work to include tasks related to autonomous driving and the use of synthetic data.

	ERF: A Benchmark Dataset for Robust Semantic Segmentation under Extreme Rainfall Conditions Xin Yang, Xin Zhang, Xinchao Wang AAAI, 2025 project page / arXiv / code A dataset for both image and video semantic segmentation methods under violent rain condition to evaluate models' robustness in extreme weather event.
	Semantic Segmentation on Raindrop Degraded Images Using Two-Stage Dual Teacher-Student Learning Xin Yang, Wending Yan, Yuan Yuan, Michael Bi Mi, Robby T. Tan AAAI, 2025 project page / arXiv / code A semantic segmentation method designed for complex raindrop degradation under heavy rain condition.
	End-to-End Video Semantic Segmentation in Adverse Weather using Fusion Blocks and Temporal-Spatial Teacher-Student Learning Xin Yang, Wending Yan, Michael Bi Mi, Yuan Yuan, Robby T. Tan NeurIPS, 2024 project page / paper / code An optical-flow-free video semantic segmentation method designed to adapt the model to various unlabeled adverse weather conditions.
	Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention Xin Yang, Wending Yan, Yuan Yuan, Michael Bi Mi, Robby T. Tan AAAI, 2024 project page / arXiv / code A semantic segmentation method designed to sequentially adapt the model to various unlabeled adverse weather conditions.
	Object Detection in Foggy Scenes by Embedding Depth and Reconstruction into Domain Adaptation Xin Yang, Michael Bi Mi, Yuan Yuan, Xin Wang, Robby T. Tan ACCV, 2022 arXiv / code A domain adaptation method for object detection under foggy condition.

Awards

[2016] 1st Place, Award in ACM programming competition in New Zealand; 10th Place, Award in ACM programming competition in Oceania

[2015] 3rd Place, Award in ACM programming competition in New Zealand

[2015] 1st Place, Award in IEEEXtreme programming competition in New Zealand

Website template stolen from Jon Barron.