Guiyu Liu
Research Subjects
Research Interests
Guiyu Liu has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Chaoqiang Ye
Huawei Noah's Ark Lab
1 shared publication Hang Xu
Huawei Noah's Ark Lab
1 shared publication- Mukun Luo
Shanghai Jiao Tong University
1 shared publication - Sihao Lin
Responsible AI Research Centre, Australian Institute for Machine Learning, The University of Adelaide, Adelaide, SA, Australia
1 shared publication - Xiaodan Liang
Shenzhen Campus of Sun Yat-sen University
1 shared publication Xiaojun Chang
University of Technology Sydney
1 shared publication
Latest Publications
- Open Access
FULLER: Unified Multi-modality Multi-task 3D Perception via Multi-level Gradient Calibration
Multi-modality fusion and multi-task learning are becoming trendy in 3D autonomous driving scenario, considering robust prediction and computation budget. However, naively extending the existing framework to the domain of multi-modality multi-task learning remains ineffective and even poisonous due to the notorious modality bias and task conflict. Previous works manually coordinate the learning framework with empirical knowledge, which may lead to sub-optima. To mitigate the issue, we propose a novel yet simple multi-level gradient calibration learning framework across tasks and modalities during optimization. Specifically, the gradients, produced by the task heads and used to update the shared backbone, will be calibrated at the backbone's last layer to alleviate the task conflict. Before the calibrated gradients are further propagated to the modality branches of the backbone, their magnitudes will be calibrated again to the same level, ensuring the downstream tasks pay balanced attention to different modalities. Experiments on large-scale benchmark nuScenes demonstrate the effectiveness of the proposed method, eg, an absolute 14.4% mIoU improvement on map segmentation and 1.4% mAP improvement on 3D detection, advancing the application of 3D autonomous driving in the domain of multi-modality fusion and multi-task learning. We also discuss the links between modalities and tasks.
Open AccessFULLER: Unified Multi-modality Multi-task 3D Perception via Multi-level Gradient Calibration
Multi-modality fusion and multi-task learning are becoming trendy in 3D autonomous driving scenario, considering robust prediction and computation budget. However, naively extending the existing framework to the domain of multi-modality multi-task learning remains ineffective and even poisonous due to the notorious modality bias and task conflict. Previous works manually coordinate the learning framework with empirical knowledge, which may lead to sub-optima. To mitigate the issue, we propose a novel yet simple multi-level gradient calibration learning framework across tasks and modalities during optimization. Specifically, the gradients, produced by the task heads and used to update the shared backbone, will be calibrated at the backbone's last layer to alleviate the task conflict. Before the calibrated gradients are further propagated to the modality branches of the backbone, their magnitudes will be calibrated again to the same level, ensuring the downstream tasks pay balanced attention to different modalities. Experiments on large-scale benchmark nuScenes demonstrate the effectiveness of the proposed method, eg, an absolute 14.4% mIoU improvement on map segmentation and 1.4% mAP improvement on 3D detection, advancing the application of 3D autonomous driving in the domain of multi-modality fusion and multi-task learning. We also discuss the links between modalities and tasks.