activity
20162023
most citedInterpreting CNN Knowledge via an Explanatory Graph

33 citations · 174 across the 39 of their papers we have counts for

collaborators
Showing cs.CVShow all

20 papers · 1 filter

cs.CV2021★ 7 cited

Interpreting Representation Quality of DNNs for 3D Point Cloud Processing

Wen Shen, Qihan Ren, Dongrui Liu +1

In this paper, we evaluate the quality of knowledge representations encoded in deep neural networks (DNNs) for 3D point cloud processing. We propose a method to disentangle the ove…

cs.CV2021

Visualizing the Emergence of Intermediate Visual Patterns in DNNs

Mingjie Li, Shaobo Wang, Quanshi Zhang

This paper proposes a method to visualize the discrimination power of intermediate-layer visual patterns encoded by a DNN. Specifically, we visualize (1) how the DNN gradually lear…

cs.CV2021★ 6 cited

Interpretable Compositional Convolutional Neural Networks

Wen Shen, Zhihua Wei, Shikun Huang +4

The reasonable definition of semantic interpretability presents the core challenge in explainable AI. This paper proposes a method to modify a traditional convolutional neural netw…

cs.CV2019

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

Wen Shen, Zhihua Wei, Shikun Huang +4

In this paper, we diagnose deep neural networks for 3D point cloud processing to explore utilities of different intermediate-layer network architectures. We propose a number of hyp…

cs.CV2019

3D-Rotation-Equivariant Quaternion Neural Networks

Wen Shen, Binbin Zhang, Shikun Huang +2

This paper proposes a set of rules to revise various neural networks for 3D point cloud processing to rotation-equivariant quaternion neural networks (REQNNs). We find that when a…

cs.CV2019★ 3 cited

Explaining AlphaGo: Interpreting Contextual Effects in Neural Networks

Zenan Ling, Haotian Ma, Yu Yang +3

In this paper, we propose to disentangle and interpret contextual effects that are encoded in a pre-trained deep neural network. We use our method to explain the gaming strategy of…