167 citations · 1k across the 81 of their papers we have counts for
7 papers · 2 filters
Explanatory Graphs for CNNs
Quanshi Zhang, Xin Wang, Ruiming Cao +3
This paper introduces a graphical model, namely an explanatory graph, which reveals the knowledge hierarchy hidden inside conv-layers of a pre-trained CNN. Each filter in a conv-la…
Mining Interpretable AOG Representations from Convolutional Networks via Active Question Answering
Quanshi Zhang, Ruiming Cao, Ying Nian Wu +1
In this paper, we present a method to mine object-part patterns from conv-layers of a pre-trained convolutional neural network (CNN). The mined object-part patterns are organized b…
Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation
Siyuan Huang, Siyuan Qi, Yinxue Xiao +3
Holistic 3D indoor scene understanding refers to jointly recovering the i) object bounding boxes, ii) room layout, and iii) camera pose, all in 3D. The existing methods either are…
Unsupervised Learning of Neural Networks to Explain Neural Networks
Quanshi Zhang, Yu Yang, Yuchen Liu +2
This paper presents an unsupervised method to learn a neural network, namely an explainer, to interpret a pre-trained convolutional neural network (CNN), i.e., explaining knowledge…
Replicating Active Appearance Model by Generator Network
Tian Han, Jiawen Wu, Ying Nian Wu
A recent Cell paper [Chang and Tsao, 2017] reports an interesting discovery. For the face stimuli generated by a pre-trained active appearance model (AAM), the responses of neurons…
Learning Descriptor Networks for 3D Shape Synthesis and Analysis
Jianwen Xie, Zilong Zheng, Ruiqi Gao +3
This paper proposes a 3D shape descriptor network, which is a deep convolutional energy-based model, for modeling volumetric shape patterns. The maximum likelihood training of the…