Softer-NMS: Rethinking Bounding Box Regression for Accurate Object Detection
share
Non-maximum suppression (NMS) is essential for state-of-the-art object detectors to localize object from a set of candidate locations. However, accurate candidate location sometimes is not associated with a high classification score, which leads to object localization failure during NMS. In this paper, we introduce a novel bounding box regression loss for learning bounding box transformation and localization variance together. The resulting localization variance exhibits a strong connection to localization accuracy, which is then utilized in our new non-maximum suppression method to improve localization accuracy for object detection. On MS-COCO, we boost the AP of VGG-16 faster R-CNN from 23.6 additional computational overhead. More importantly, our method is able to improve the AP of ResNet-50 FPN fast R-CNN from 36.8 state-of-the-art bounding box refinement result.
READ FULL TEXT
