Corner Proposal Network for Anchor-free, Two-stage Object Detection
It addresses the problem of improving recall and precision in object detection for computer vision applications, with incremental improvements in efficiency and accuracy.
This paper tackles object detection by proposing an anchor-free, two-stage framework that extracts object proposals using corner keypoints and classifies them separately, achieving competitive performance on MS-COCO with an AP of 49.2% and efficient speeds up to 43.3 FPS.
The goal of object detection is to determine the class and location of objects in an image. This paper proposes a novel anchor-free, two-stage framework which first extracts a number of object proposals by finding potential corner keypoint combinations and then assigns a class label to each proposal by a standalone classification stage. We demonstrate that these two stages are effective solutions for improving recall and precision, respectively, and they can be integrated into an end-to-end network. Our approach, dubbed Corner Proposal Network (CPN), enjoys the ability to detect objects of various scales and also avoids being confused by a large number of false-positive proposals. On the MS-COCO dataset, CPN achieves an AP of 49.2% which is competitive among state-of-the-art object detection methods. CPN also fits the scenario of computational efficiency, which achieves an AP of 41.6%/39.7% at 26.2/43.3 FPS, surpassing most competitors with the same inference speed. Code is available at https://github.com/Duankaiwen/CPNDet