Learning from Ambiguously Labeled Images

13 years 7 months ago
Learning from Ambiguously Labeled Images
In many image and video collections, we have access only to partially labeled data. For example, personal photo collections often contain several faces per image and a caption that only specifies who is in the picture, but not which name matches which face. Similarly, movie screenplays can tell us who is in the scene, but not when and where they are on the screen. We formulate the learning problem in this setting as partially-supervised multiclass classification where each instance is labeled ambiguously with more than one label. We show theoretically that effective learning is possible under reasonable assumptions even when all the data is weakly labeled. Motivated by the analysis, we propose a general convex learning formulation based on minimization of a surrogate loss appropriate for the ambiguous label setting. We apply our framework to identifying faces culled from web news sources and to naming characters in TV series and movies. We experiment on a very large dat...
Benjamin Sapp, Benjamin Taskar, Chris Jordan, Timo
Added 09 May 2009
Updated 10 Dec 2009
Type Conference
Year 2009
Where CVPR
Authors Benjamin Sapp, Benjamin Taskar, Chris Jordan, Timothee Cour
Comments (0)