Title :
Sharing features between objects and their attributes
Author :
Hwang, Sung Ju ; Sha, Fei ; Grauman, Kristen
Author_Institution :
Dept. of Comput. Sci., Univ. of Texas at Austin, Austin, TX, USA
Abstract :
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 attribute-and object-labeled image data, we learn a shared lower-dimensional 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 of the ultimate object classifiers. We validate the approach on datasets of animals and outdoor scenes, and show significant improvements over traditional multi-class object classifiers and direct attribute prediction models.
Keywords :
learning (artificial intelligence); object recognition; pattern classification; attribute-labeled image; convex multitask feature learning; direct attribute prediction model; human-defined semantics; kernelized formulation; low-level visual feature space; multiclass object classifier; object recognition; object-labeled image; task-specific classifier parameter; visual attribute; Animals; Kernel; Optimization; Predictive models; Training; Vectors; Visualization;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on
Conference_Location :
Providence, RI
Print_ISBN :
978-1-4577-0394-2
DOI :
10.1109/CVPR.2011.5995543