Author name cluster

Ruiming Cao

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

1 author row

AAAI Conference 2018 Conference Paper

Interpreting CNN Knowledge via an Explanatory Graph

Quanshi Zhang
Ruiming Cao
Feng Shi
Ying Nian Wu
Song-Chun Zhu

This paper learns a graphical model, namely an explanatory graph, which reveals the knowledge hierarchy hidden inside a pre-trained CNN. Considering that each ﬁlter1 in a convlayer of a pre-trained CNN usually represents a mixture of object parts, we propose a simple yet efﬁcient method to automatically disentangles different part patterns from each ﬁlter, and construct an explanatory graph. In the explanatory graph, each node represents a part pattern, and each edge encodes co-activation relationships and spatial relationships between patterns. More importantly, we learn the explanatory graph for a pre-trained CNN in an unsupervised manner, i. e. without a need of annotating object parts. Experiments show that each graph node consistently represents the same object part through different images. We transfer part patterns in the explanatory graph to the task of part localization, and our method signiﬁcantly outperforms other approaches.

PDF Details

AAAI Conference 2017 Conference Paper

Growing Interpretable Part Graphs on ConvNets via Multi-Shot Learning

Quanshi Zhang
Ruiming Cao
Ying Nian Wu
Song-Chun Zhu

This paper proposes a learning strategy that extracts objectpart concepts from a pre-trained convolutional neural network (CNN), in an attempt to 1) explore explicit semantics hidden in CNN units and 2) gradually grow a semantically interpretable graphical model on the pre-trained CNN for hierarchical object understanding. Given part annotations on very few (e. g. 3–12) objects, our method mines certain latent patterns from the pre-trained CNN and associates them with different semantic parts. We use a four-layer And-Or graph to organize the mined latent patterns, so as to clarify their internal semantic hierarchy. Our method is guided by a small number of part annotations, and it achieves superior performance (about 13%–107% improvement) in part center prediction on the PASCAL VOC and ImageNet datasets1.

PDF Details