Corner Proposal Network for Anchor-free, Two-stage Object Detection

TL;DR

This paper introduces the Corner Proposal Network (CPN), an anchor-free, two-stage object detection framework that improves detection accuracy and efficiency by proposing object corners and classifying proposals end-to-end.

Contribution

The paper presents a novel anchor-free, two-stage detection framework that effectively combines corner proposals with classification, enhancing recall, precision, and computational efficiency.

Findings

Achieves 49.2% AP on MS-COCO, competitive with state-of-the-art methods.

Runs at 26.2 FPS with 41.6% AP, surpassing similar-speed competitors.

Effectively detects objects of various scales and reduces false positives.

Abstract

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