K
Kaisheng Ma
Researcher at Tsinghua University
Publications - 100
Citations - 2629
Kaisheng Ma is an academic researcher from Tsinghua University. The author has contributed to research in topics: Computer science & Pruning (decision trees). The author has an hindex of 20, co-authored 73 publications receiving 1513 citations. Previous affiliations of Kaisheng Ma include Pennsylvania State University & Peking University.
Papers
More filters
Proceedings ArticleDOI
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?
TL;DR: Dong et al. as discussed by the authors showed that foundational Transformers pretrained with 2D images or natural languages can help self-supervised 3D representation learning through training Autoencoders as Cross-Modal Teachers (ACT).
Posted Content
An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices
Xiaolong Ma,Wei Niu,Tianyun Zhang,Sijia Liu,Sheng Lin,Hongjia Li,Xiang Chen,Jian Tang,Kaisheng Ma,Bin Ren,Yanzhi Wang +10 more
TL;DR: This work introduces a new sparsity dimension, namely pattern-based sparsity that comprises pattern and connectivity sparsity, and is the first time that mobile devices achieve real-time inference for the large-scale DNN models thanks to the unique spatial property of pattern- based sparsity and the help of the code generation capability of compilers.
Proceedings Article
Improve Object Detection with Feature-based Knowledge Distillation: Towards Accurate and Efficient Detectors
Linfeng Zhang,Kaisheng Ma +1 more
TL;DR: Zhang et al. as discussed by the authors proposed attention-guided and non-local distillation to solve the problem of imbalance between pixels of foreground and background and lack of distillation on the relation between different pixels.
Proceedings ArticleDOI
Contrastive Deep Supervision
TL;DR: A novel training framework named Contrastive Deep Supervision is proposed, which supervises the intermediate layers with augmentation-based contrastive learning, which has effects on general image classification, fine-grained image classification and object detection in supervised learning, semi-supervised learning and knowledge distillation.
Journal ArticleDOI
Ultra-low power dissipation of improved complementary pass-transistor adiabatic logic circuits based on FinFETs
TL;DR: A novel improved complementary pass-transistor adiabatic logic (ICPAL) based on fin-type field-effect transistor (FinFET) devices with ultra-low power dissipation has been presented and supports a better pre-evaluation of system power Dissipation in VLSI design.