Weakly-supervised Discovery of Visual Pattern Configurations

06/25/2014
by   Hyun Oh Song, et al.
0

The increasing prominence of weakly labeled data nurtures a growing demand for object detection methods that can cope with minimal supervision. We propose an approach that automatically identifies discriminative configurations of visual patterns that are characteristic of a given object class. We formulate the problem as a constrained submodular optimization problem and demonstrate the benefits of the discovered configurations in remedying mislocalizations and finding informative positive and negative training examples. Together, these lead to state-of-the-art weakly-supervised detection results on the challenging PASCAL VOC dataset.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset