106 citations · 565 across the 31 of their papers we have counts for
9 papers · 1 filter
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…
DPPMask: Masked Image Modeling with Determinantal Point Processes
Junde Xu, Zikai Lin, Donghao Zhou +5
Masked Image Modeling (MIM) has achieved impressive representative performance with the aim of reconstructing randomly masked images. Despite the empirical success, most previous w…
Traj-MAE: Masked Autoencoders for Trajectory Prediction
Hao Chen, Jiaze Wang, Kun Shao +5
Trajectory prediction has been a crucial task in building a reliable autonomous driving system by anticipating possible dangers. One key issue is to generate consistent trajectory…
PointPatchMix: Point Cloud Mixing with Patch Scoring
Yi Wang, Jiaze Wang, Jinpeng Li +4
Data augmentation is an effective regularization strategy for mitigating overfitting in deep neural networks, and it plays a crucial role in 3D vision tasks, where the point cloud…
RepMode: Learning to Re-parameterize Diverse Experts for Subcellular Structure Prediction
Donghao Zhou, Chunbin Gu, Junde Xu +4
In biological research, fluorescence staining is a key technique to reveal the locations and morphology of subcellular structures. However, it is slow, expensive, and harmful to ce…
Pseudo-label Guided Cross-video Pixel Contrast for Robotic Surgical Scene Segmentation with Limited Annotations
Yang Yu, Zixu Zhao, Yueming Jin +3
Surgical scene segmentation is fundamentally crucial for prompting cognitive assistance in robotic surgery. However, pixel-wise annotating surgical video in a frame-by-frame manner…
Acknowledging the Unknown for Multi-label Learning with Single Positive Labels
Donghao Zhou, Pengfei Chen, Qiong Wang +2
Due to the difficulty of collecting exhaustive multi-label annotations, multi-label datasets often contain partial labels. We consider an extreme of this weakly supervised learning…
A Rotation-Invariant Framework for Deep Point Cloud Analysis
Xianzhi Li, Ruihui Li, Guangyong Chen +3
Recently, many deep neural networks were designed to process 3D point clouds, but a common drawback is that rotation invariance is not ensured, leading to poor generalization to ar…
Blind Image Denoising via Dependent Dirichlet Process Tree
Fengyuan Zhu, Guangyong Chen, Jianye Hao +1
Most existing image denoising approaches assumed the noise to be homogeneous white Gaussian distributed with known intensity. However, in real noisy images, the noise models are us…