A Classification Leveraged Object Detector
This work addresses a specific problem in computer vision by enhancing object detection accuracy, but it is incremental as it builds on existing methods.
The paper tackled the performance gap between image classification and object detection by proposing a method to leverage classification on regions from a preliminary detector, improving average precision from 35.9% to 39.5% on PASCAL VOC 2007.
Currently, the state-of-the-art image classification algorithms outperform the best available object detector by a big margin in terms of average precision. We, therefore, propose a simple yet principled approach that allows us to leverage object detection through image classification on supporting regions specified by a preliminary object detector. Using a simple bag-of- words model based image classification algorithm, we leveraged the performance of the deformable model objector from 35.9% to 39.5% in average precision over 20 categories on standard PASCAL VOC 2007 detection dataset.