Ping Zhao — accepted AI-conference papers

2021

Interpretable Compositional Convolutional Neural Networks

Wen Shen, Zhihua Wei, Shikun Huang, Binbin Zhang, Jiaqi Fan, Ping Zhao +1

IJCAI 2021poster

This paper proposes a method to modify a traditional convolutional neural network (CNN) into an interpretable compositional CNN, in order to learn filters that encode meaningful visual patterns in intermediate convolutional layers. In a compositional CNN, each filter is supposed to consistently repr…

Cited by 41 Source ↗PDF ↗code ↗Scholar ↗

2021

Verifiability and Predictability: Interpreting Utilities of Network Architectures for Point Cloud Processing

Wen Shen, Zhihua Wei, Shikun Huang, Binbin Zhang, Panyue Chen, Ping Zhao +1

CVPR 2021poster

In this paper, we diagnose deep neural networks for 3D point cloud processing to explore utilities of different network architectures. We propose a number of hypotheses on the effects of specific network architectures on the representation capacity of DNNs. In order to prove the hypotheses, we desig…

Cited by 4 PDF ↗Scholar ↗