Sciweavers

Share
CVPR
2011
IEEE

Sharing Features Between Objects and Their Attributes

8 years 2 months ago
Sharing Features Between Objects and Their Attributes
Visual attributes expose human-defined semantics to object recognition models, but existing work largely restricts their influence to mid-level cues during classifier training. Rather than treat attributes as intermediate features, we consider how learning visual properties in concert with object categories can regularize the models for both. Given a low-level visual feature space together with attributeand object-labeled image data, we learn a shared lowerdimensional representation by optimizing a joint loss function that favors common sparsity patterns across both types of prediction tasks. We adopt a recent kernelized formulation of convex multi-task feature learning, in which one alternates between learning the common features and learning task-specific classifier parameters on top of those features. In this way, our approach discovers any structure among the image descriptors that is relevant to both tasks, and allows the top-down semantics to restrict the hypothesis space o...
Sung Ju Hwang, Fei Sha, Kristen Grauman
Added 08 Apr 2011
Updated 29 Apr 2011
Type Journal
Year 2011
Where CVPR
Authors Sung Ju Hwang, Fei Sha, Kristen Grauman
Comments (0)
books