Computer Science – Computer Vision and Pattern Recognition
Scientific paper
2011-10-24
Computer Science
Computer Vision and Pattern Recognition
14 pages, 11 figures
Scientific paper
Scene understanding includes many related sub-tasks, such as scene categorization, depth estimation, object detection, etc. Each of these sub-tasks is often notoriously hard, and state-of-the-art classifiers already exist for many of them. These classifiers operate on the same raw image and provide correlated outputs. It is desirable to have an algorithm that can capture such correlation without requiring any changes to the inner workings of any classifier. We propose Feedback Enabled Cascaded Classification Models (FE-CCM), that jointly optimizes all the sub-tasks, while requiring only a `black-box' interface to the original classifier for each sub-task. We use a two-layer cascade of classifiers, which are repeated instantiations of the original ones, with the output of the first layer fed into the second layer as input. Our training method involves a feedback step that allows later classifiers to provide earlier classifiers information about which error modes to focus on. We show that our method significantly improves performance in all the sub-tasks in the domain of scene understanding, where we consider depth estimation, scene categorization, event categorization, object detection, geometric labeling and saliency detection. Our method also improves performance in two robotic applications: an object-grasping robot and an object-finding robot.
Chen Tsuhan
Kowdle Adarsh
Li Congcong
Saxena Ashutosh
No associations
LandOfFree
Towards Holistic Scene Understanding: Feedback Enabled Cascaded Classification Models does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Towards Holistic Scene Understanding: Feedback Enabled Cascaded Classification Models, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Towards Holistic Scene Understanding: Feedback Enabled Cascaded Classification Models will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-519188