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

By Kaiwen Duan, Lingxi Xie, Honggang Qi, Song Bai, Qingming Huang, Qi Tian. 2020

117 citations recorded by the source corpus.

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 this https URL

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Chunhua Shen
2. Hao Chen
3. Zhi Tian
4. Tong He
5. Philipp Krahenbuhl
6. Xingyi Zhou
7. Vladlen Koltun
8. Trevor Darrell

In Computer Vision and Pattern Recognition

1. Chunhua Shen
2. Luc Van Gool
3. Xiaogang Wang
4. Vladlen Koltun
5. Dacheng Tao
6. Ming-Hsuan Yang
7. Alan L. Yuille
8. Trevor Darrell

Citations in the corpus

• FCOS: A Simple and Strong Anchor-Free Object Detector (2020, methodology): “to get the target boxes. In contrast, FCOS is a concise and very straightforward method for box detection. After the submission of this work, some new anchorfree detectors appeared. For instance, CPN [36] replaces the region proposal networks (RPNs) in two-stage detectors with bottom-up anchor-free ”
• Probabilistic two-stage detection (2021, methodology): “In the first stage, a Region Proposal Network (RPN) learns to classify annotated objects b i as foreground and other boxes as background.”