Jiakang Yuan
I am a second-year Ph.D. student in the School of Information Science and Technology, Fudan University, under Prof. Tao Chen. I work in the fields of deep learning and computer vision, with particular focuses on 3D perception and transfer learning. My research pursues to build robust and scalable perception models and find unified representation that can be generalized across different domains and scenarios, with minimum or no human annotations needed.
I am fortunate to have research attachments and internships at Shanghai AI Lab.
News
2024.01 One Paper (ResimAD) is accepted by ICLR 2024.
2023.09 One Paper (AD-PT) is accepted by NeurIPS 2023.
2023.02 Two Papers (Bi3D and Uni3D) are accepted by CVPR 2023.
2022.07 One Paper (HelixFormer) is accepted by ACM’MM 2022.
Recent Publications
AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset
Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detection
Uni3D: A Unified Baseline for Multi-dataset 3D Object Detection
Learning Cross-image Semantic Relation in Transformer for Few-shot Fine-grained Image Classification
Priprints
UniDA3D: Unified Domain Adaptive 3D Semantic Segmentation Pipeline
SPOT: Scalable 3D Pre-training via Occupancy Prediction for Autonomous Driving
Education
2022.08 - Present Ph.D., School of Information Science and Technology
2018.09 - 2022.06 B.Eng., School of Information Science and Technology