Attributes for classifier feedback
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Augmented attribute representations
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Attribute learning for understanding unstructured social activity
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
Unsupervised learning of discriminative relative visual attributes
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
| Hi-index | 0.00 |
We present a new approach to learning attribute-based descriptions of objects. Unlike earlier works, we do not assume that the descriptions are hand-labeled. Instead, our approach jointly learns both the attribute classifiers and the descriptions from data. By incorporating class information into the attribute classifier learning, we get an attribute-level representation that generalizes well to both unseen examples of known classes and unseen classes. We consider two different settings, one with unlabeled images available for learning, and another without. The former corresponds to a novel transductive setting where the unlabeled images can come from new classes. Results from Animals with Attributes and a-Yahoo, a-Pascal benchmark datasets show that the learned representations give similar or even better accuracy than the hand-labeled descriptions.