An anchor box setting technique based on differences between categories for object detection

Detection accuracy and speed are crucial in object detection in computer vision. This work proposes a novel technique called On-Category Anchors (OC-Anchors) to improve the accuracy of real-time single-stage object detectors. The key concept of the OC-Anchors technique is to create anchors based on the categories of foreground objects. The OC-Anchors are set to reflect the bounding box features of the foreground object category. This approach improves the accuracy of predicting the bounding boxes of objects. The performance of the proposed OC-Anchors technique is examined in detail in the YOLOv2 framework with the COCO dataset. The results show that the OC-Anchors technique significantly improves the detection accuracy in tests on COCO test-dev, without substantially affecting the prediction speed. The improvement in average precision ranges from 21.6 to 27.1%.

Automated summary

The novel technique OC-Anchors is proposed to improve the accuracy of real-time single-stage object detectors by creating anchors based on the categories of foreground objects. The performance of OC-Anchors in the YOLOv2 framework with COCO dataset shows significant improvement in detection accuracy without affecting prediction speed.