Multistage Object Detection With Group Recursive Learning
Citations Over TimeTop 10% of 2017 papers
Abstract
Most existing detection pipelines treat object proposals independently and predict bounding box locations and classification scores over them separately. However, the important semantic and spatial layout correlations among proposals are often ignored, which are actually useful for more accurate object detection. In this paper, we propose a new EM-like group recursive learning approach to iteratively refine object proposals by incorporating such context of surrounding proposals and provide an optimal spatial configuration of object detections. In addition, we propose to incorporate the weakly supervised object segmentation cues and region-based object detection into a multistage architecture in order to fully exploit the learned segmentation features for better object detection in an end-toend way. The proposed architecture consists of three cascaded networks that, respectively, learn to perform weakly supervised object segmentation, object proposal generation, and recursive detection refinement. Combining the group recursive learning and the multistage architecture provides competitive mAPs of 78.7% and 74.9% on the PASCAL VOC2007 and VOC2012 datasets, respectively, which outperform many well-established baselines significantly.
Related Papers
- → Syncretic-NMS: A Merging Non-Maximum Suppression Algorithm for Instance Segmentation(2020)30 cited
- → Medical Image Segmentation with Imperfect 3D Bounding Boxes(2021)1 cited
- → Bounding-box Centralization for Improving SiamFC++(2021)1 cited
- A Method to Generate the Minimum Bounding Boxes for Shape-Arbitrary Objects(2010)