Human-Debugging of Machines

We have proposed the human-debugging paradigm, where human involvement is leveraged to identify bottlenecks in existing computational AI systems. We introduce this paradigm, and briefly describe two instances of our prior work on using this paradigm for computer vision tasks. We then describe some interesting challenges involved in employing this paradigm in practice.

[1]  Herman Chernoff,et al.  The Use of Faces to Represent Points in k- Dimensional Space Graphically , 1973 .

[2]  Daniel A. Keim,et al.  HD-Eye: Visual Mining of High-Dimensional Data , 1999, IEEE Computer Graphics and Applications.

[3]  Tsuhan Chen,et al.  From appearance to context-based recognition: Dense labeling in small images , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  C. Lawrence Zitnick,et al.  The role of features, algorithms and data in visual recognition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  Devi Parikh.  Recognizing jumbled images: The role of local and global information in image classification , 2011, 2011 International Conference on Computer Vision.

[7]  C. Lawrence Zitnick,et al.  Finding the weakest link in person detectors , 2011, CVPR 2011.

[8]  Tsuhan Chen,et al.  Extracting adaptive contextual cues from unlabeled regions , 2011, 2011 International Conference on Computer Vision.