.png){kind=icon}
Return
Sharing visual features for multiclass and multiview object detection
.png){kind=icon}
OA
AI
DOI：10.1109/TPAMI.2007.1055.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We consider the problem of detecting a large number of different classes of objects in cluttered scenes. Traditional approaches require applying a battery of different classifiers to the image, at multiple locations and scales. This can be slow and can require a lot of training data since each classifier requires the computation of many different image features. In particular, for independently trained detectors, the ( runtime) computational complexity and the ( training-time) sample complexity scale linearly with the number of classes to be detected. We present a multitask learning procedure, based on boosted decision stumps, that reduces the computational and sample complexity by finding common features that can be shared across the classes ( and/or views). The detectors for each class are trained jointly, rather than independently. For a given performance level, the total number of features required and, therefore, the runtime cost of the classifier, is observed to scale approximately logarithmically with the number of classes. The features selected by joint training are generic edge-like features, whereas the features chosen by training each class separately tend to be more object-specific. The generic features generalize better and considerably reduce the computational cost of multiclass object detection.
Keywords:
object detection
interclass transfer
sharing features
boosting
multiclass
Journal
IF:
18.6
Papers:
1.1K
Citations:
9.8W
Organization
No organization information available
Cited Papers
ShareSaveMyth: Intravenous amiodarone is safe in patients with atrial fibrillation and Wolff–Parkinson–White syndrome in the emergency department.png)
CJEM
OAAI
CJEMIF0
OAAIShareSaveRadiofrequency ablation of left-sided accessory pathways: Transaortic versus transseptal approach
PREAI
ShareSaveShareSave
View more