Publications

Runpei Dong, Zekun Qi, Linfeng Zhang, Junbo Zhang, Jianjian Sun, Zheng Ge, Li Yi, Kaisheng Ma
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?.
In The 11th International Conference on Learning Representations (ICLR), 2023.

PDF Cite Code

Linfeng Zhang, Xin Chen, Junbo Zhang, Runpei Dong, Kaisheng Ma
Contrastive Deep Supervision.
In The 17th European Conference on Computer Vision (ECCV), 2022. (Oral 2.7%)

PDF Cite Code

Linfeng Zhang, Xin Chen, Runpei Dong, Kaisheng Ma
Region-aware Knowledge Distillation for Efficient Image-to-Image Translation.
Tech Report, May. 2022.

PDF Cite Code

Linfeng Zhang , Runpei Dong , Hung-Shuo Tai, Kaisheng Ma
PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection.
Tech Report, May. 2022.

PDF Cite Code

Runpei Dong , Zhanhong Tan , Mengdi Wu, Linfeng Zhang, Kaisheng Ma
Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks.
In The 39th International Conference on Machine Learning (ICML), 2022.

PDF Cite Code

Sia Huat Tan, Runpei Dong, Kaisheng Ma
Multi-Glimpse Network: A Robust and Efficient Classification Architecture based on Recurrent Downsampled Attention.
In The 32nd British Machine Vision Conference (BMVC), 2021.

PDF Cite Code

Zhanhong Tan, Hongyu Cai, Runpei Dong, Kaisheng Ma
NN-Baton: DNN Workload Orchestration and Chiplet Granularity Exploration for Multichip Accelerators.
In ACM/IEEE 48th Annual International Symposium on Computer Architecture (ISCA), 2021.

PDF Cite DOI