Publication

Given a convolutional neural network (CNN) that is pre-trained for object classification, this paper proposes to use active question-answering to weakly-supervised semanticize neural patterns in conv-layers of the CNN and mine part concepts. For each part concept, we mine neural patterns in the pre-trained CNN, which are related to the target part, and use these patterns to construct an And-Or graph (AOG) to represent the target part. The And-Or graph (AOG) represents a four-layer semantic hierarchy of a part as a white-box model, which associates different CNN units with different part/sub-part semantics. We start an active human-computer communication to incrementally grow such an AOG on the pre-trained CNN as follows. We allow the computer to actively detect objects, whose neural patterns cannot be explained by the current AOG. Then, the computer asks human about the unexplained objects, and uses the answers to automatically discover certain CNN patterns corresponding to the missing knowledge. We incrementally grow new sub-AOG branches to encode new knowledge discovered during the active-learning process. In experiments, our method exhibited great learning efficiency. Our method used about 1/6 of the part annotations for training, but achieved similar or even much better part-localization performance than fast-RCNN methods on the PASCAL VOC Part dataset and the CUB200-2011 dataset.
In Proceedings of CVPR-17

This paper proposes a learning strategy that extracts object-part 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 datasets.
In Proceedings of AAAI-17

Recent Posts

I migrated my original site hosted on Google Sites to here on Github Pages. It will hopefully provide better accessibility for visitors from regions where Google has been blocked (i.e. China).

CONTINUE READING

Contact

Email: caoruiming[at]gmail[dot]com