Z
Zhiwu Lu
Researcher at Renmin University of China
Publications - 154
Citations - 2972
Zhiwu Lu is an academic researcher from Renmin University of China. The author has contributed to research in topics: Computer science & Graph (abstract data type). The author has an hindex of 25, co-authored 134 publications receiving 1897 citations. Previous affiliations of Zhiwu Lu include City University of Hong Kong & Peking University.
Papers
More filters
Posted Content
Counterfactual VQA: A Cause-Effect Look at Language Bias
TL;DR: A novel counterfactual inference framework is proposed, which enables the language bias to be captured as the direct causal effect of questions on answers and reduced by subtracting the direct language effect from the total causal effect.
Journal ArticleDOI
Pre-Trained Models: Past, Present and Future
Xu Han,Zhengyan Zhang,Ning Ding,Yuxian Gu,Xiao Liu,Yuqi Huo,Jiezhong Qiu,Liang Zhang,Wentao Han,Minlie Huang,Qin Jin,Yanyan Lan,Yang Liu,Zhiyuan Liu,Zhiwu Lu,Xipeng Qiu,Ruihua Song,Jie Tang,Ji-Rong Wen,Jinhui Yuan,Wayne Xin Zhao,Jun Zhu +21 more
TL;DR: In this paper, the authors take a deep look into the history of pre-training, especially its special relation with transfer learning and self-supervised learning, to reveal the crucial position of PTMs in the AI development spectrum.
Proceedings ArticleDOI
Learning Depth-Guided Convolutions for Monocular 3D Object Detection
TL;DR: D4LCN overcomes the limitation of conventional 2D convolutions and narrows the gap between image representation and 3D point cloud representation, where the filters and their receptive fields can be automatically learned from image-based depth maps.
Posted Content
Learning Depth-Guided Convolutions for Monocular 3D Object Detection
TL;DR: D4LCN overcomes the limitation of conventional 2D convolutions and narrows the gap between image representation and 3D point cloud representation, where the filters and their receptive fields can be automatically learned from image-based depth maps.
Proceedings ArticleDOI
Large-Scale Few-Shot Learning: Knowledge Transfer With Class Hierarchy
TL;DR: This work proposes a novel large-scale FSL model by learning transferable visual features with the class hierarchy which encodes the semantic relations between source and target classes and significantly outperforms not only the NN baseline but also the state-of-the-art alternatives.