collaborators

5 papers

cs.CV2025

P3P: Pseudo-3D Pre-training for Scaling 3D Voxel-based Masked Autoencoders

Xuechao Chen, Ying Chen, Jialin Li +5

3D pre-training is crucial to 3D perception tasks. Nevertheless, limited by the difficulties in collecting clean and complete 3D data, 3D pre-training has persistently faced data s…

cs.CV2024

Anno-incomplete Multi-dataset Detection

Yiran Xu, Haoxiang Zhong, Kai Wu +5

Object detectors have shown outstanding performance on various public datasets. However, annotating a new dataset for a new task is usually unavoidable in real, since 1) a single e…

cs.CV2024

Distribution-Aware Calibration for Object Detection with Noisy Bounding Boxes

Donghao Zhou, Jialin Li, Jinpeng Li +7

Large-scale well-annotated datasets are of great importance for training an effective object detector. However, obtaining accurate bounding box annotations is laborious and demandi…

cs.LG2024

Decision Boundary-aware Knowledge Consolidation Generates Better Instance-Incremental Learner

Qiang Nie, Weifu Fu, Yuhuan Lin +5

Instance-incremental learning (IIL) focuses on learning continually with data of the same classes. Compared to class-incremental learning (CIL), the IIL is seldom explored because…

cs.CV2024

IIDM: Inter and Intra-domain Mixing for Semi-supervised Domain Adaptation in Semantic Segmentation

Weifu Fu, Qiang Nie, Jialin Li +6

Despite recent advances in semantic segmentation, an inevitable challenge is the performance degradation caused by the domain shift in real applications. Current dominant approach…