Dinesh Jayaraman
Dinesh Jayaraman
Home
Research Group
Publications
Teaching
Generalization
Divide, Share, and Conquer: Multi-Task Attribute Learning With Selective Sharing
We explain how visual attribute learning may benefit from multi-task/transfer learning approaches that carefully select what to share among whom. We show that such methods can combat noisy correlations among attributes, and variations among attribute appearances across object categories.
Dinesh Jayaraman
,
Chao-Yeh Chen*
,
Fei Sha
,
Kristen Grauman
Decorrelating Semantic Visual Attributes by Resisting the Urge to Share
While learning multiple attributes with possibly noisy correlations in the training set, it helps to employ a multi-task learning approach that tries to learn classifiers that rely on different parts of the input feature space.
Dinesh Jayaraman
,
Fei Sha
,
Kristen Grauman
Cite
×