Timezone: »

 
Poster
Weakly-supervised Discovery of Visual Pattern Configurations
Hyun Oh Song · Yong Jae Lee · Stefanie Jegelka · Trevor Darrell

Mon Dec 08 04:00 PM -- 08:59 PM (PST) @ Level 2, room 210D
in Poster Session and Reception »

The prominence of weakly labeled data gives rise to 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.

[ PDF] 

Author Information

Hyun Oh Song (Seoul National University)
Yong Jae Lee (UC Davis)
Stefanie Jegelka (MIT)
Trevor Darrell (UC Berkeley)

More from the Same Authors