167 citations · 1k across the 81 of their papers we have counts for
5 papers · 2 filters
Interpretable Convolutional Neural Networks
Quanshi Zhang, Ying Nian Wu, Song-Chun Zhu
This paper proposes a method to modify traditional convolutional neural networks (CNNs) into interpretable CNNs, in order to clarify knowledge representations in high conv-layers o…
Mining Deep And-Or Object Structures via Cost-Sensitive Question-Answer-Based Active Annotations
Quanshi Zhang, Ying Nian Wu, Hao Zhang +1
This paper presents a cost-sensitive active Question-Answering (QA) framework for learning a nine-layer And-Or graph (AOG) from web images. The AOG explicitly represents object cat…
Interpreting CNN Knowledge via an Explanatory Graph
Quanshi Zhang, Ruiming Cao, Feng Shi +2
This paper learns a graphical model, namely an explanatory graph, which reveals the knowledge hierarchy hidden inside a pre-trained CNN. Considering that each filter in a conv-laye…
Interactively Transferring CNN Patterns for Part Localization
Quanshi Zhang, Ruiming Cao, Shengming Zhang +3
In the scenario of one/multi-shot learning, conventional end-to-end learning strategies without sufficient supervision are usually not powerful enough to learn correct patterns fro…
Mining Object Parts from CNNs via Active Question-Answering
Quanshi Zhang, Ruiming Cao, Ying Nian Wu +1
Given a convolutional neural network (CNN) that is pre-trained for object classification, this paper proposes to use active question-answering to semanticize neural patterns in con…