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.
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.
In Proceedings of AAAI-17

Recent Posts

I migrated my original site hosted on Google Sites to here on Github Pages.



I am a teaching assistant for the following course at UCLA:

  • Fall 2017 CS174A: Introduction to Computer Graphics


Email: ruimingc[at]ucla[dot]edu