# CPM R-CNN: Calibrating Point-guided Misalignment in Object Detection

arXiv: https://arxiv.org/abs/2003.03570 · HTML: https://mlsanity.com/paper/2003.03570/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Mar 2020.

## Built on by (most cited first, 4 of 4)

- [Quality-Aware Network for Human Parsing](https://mlsanity.com/paper/2103.05997/) (2021)
- [TIVE: A Toolbox for Identifying Video Instance Segmentation Errors](https://mlsanity.com/paper/2210.08856/) (2022)
- [Progressive Hard-case Mining across Pyramid Levels for Object Detection](https://mlsanity.com/paper/2109.07217/) (2021)
- [UV R-CNN: Stable and Efficient Dense Human Pose Estimation](https://mlsanity.com/paper/2211.02337/) (2022)

## Abstract (arXiv)

In object detection, offset-guided and point-guided regression dominate anchor-based and anchor-free method separately. Recently, point-guided approach is introduced to anchor-based method. However, we observe points predicted by this way are misaligned with matched region of proposals and score of localization, causing a notable gap in performance. In this paper, we propose CPM R-CNN which contains three efficient modules to optimize anchor-based point-guided method. According to sufficient evaluations on the COCO dataset, CPM R-CNN is demonstrated efficient to improve the localization accuracy by calibrating mentioned misalignment. Compared with Faster R-CNN and Grid R-CNN based on ResNet-101 with FPN, our approach can substantially improve detection mAP by 3.3% and 1.5% respectively without whistles and bells. Moreover, our best model achieves improvement by a large margin to 49.9% on COCO test-dev. Code and models will be publicly available.