CPM R-CNN: Calibrating Point-guided Misalignment in Object Detection
This work addresses a specific performance gap in object detection for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of misalignment between predicted points and matched regions in anchor-based point-guided object detection, proposing CPM R-CNN to calibrate this issue, which improves detection mAP by up to 3.3% on COCO.
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.