Hot Anchors: A Heuristic Anchors Sampling Method in RCNN-Based Object Detection
AbstractIn the image object detection task, a huge number of candidate boxes are generated to match with a relatively very small amount of ground-truth boxes, and through this method the learning samples can be created. But in fact the vast majority of the candidate boxes do not contain valid object instances and should be recognized and rejected during the training and evaluation of the network. This leads to extra high computation burden and a serious imbalance problem between object and none-object samples, thereby impeding the algorithm’s performance. Here we propose a new heuristic sampling method to generate candidate boxes for two-stage detection algorithms. It is generally applicable to the current two-stage detection algorithms to improve their detection performance. Experiments on COCO dataset showed that, relative to the baseline model, this new method could significantly increase the detection accuracy and efficiency. View Full-Text
Share & Cite This Article
Zhang, J.; Zhang, J.; Yu, S. Hot Anchors: A Heuristic Anchors Sampling Method in RCNN-Based Object Detection. Sensors 2018, 18, 3415.
Zhang J, Zhang J, Yu S. Hot Anchors: A Heuristic Anchors Sampling Method in RCNN-Based Object Detection. Sensors. 2018; 18(10):3415.Chicago/Turabian Style
Zhang, Jinpeng; Zhang, Jinming; Yu, Shan. 2018. "Hot Anchors: A Heuristic Anchors Sampling Method in RCNN-Based Object Detection." Sensors 18, no. 10: 3415.
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.