Standard sliding window based object detection requires dense classifier evaluation on
densely sampled locations in scale space in order to achieve an accurate localization. To
avoid such dense evaluation, selective search based algorithms only evaluate the classifier
on a small subset of object proposals. Notwithstanding the demonstrated success, object
proposals do not guarantee perfect overlap with the object, leading to a suboptimal
detection accuracy. To address this issue, we propose to first relax the dense sampling of …

1. To accurately localize the objects in the image→ sliding window based detectors→
computational cost is too high. 2. To reduce the computational cost→ top-down or bottom-up
approaches→ none of these methods search for the object in the full continuous parameter
space, ie, the center point, scale, and aspect ratio of the object.