Skip to main content

Table 2 Performance comparisons between the well-known object detection networks and that presented in this paper

From: An improved object detection algorithm based on multi-scaled and deformable convolutional neural networks

Network model-image sizeTrainTestMAP@.50IOUFPS
Faster R-CNN-600VOC07+1207 test52.405
YOLOv1-416VOC1239.6045
SSD-500VOC1241.0218
YOLOv3-416VOC07+1248.4730
Ours-416VOC07+1252.5527
Ours-600VOC07+1255.3021
  1. Italic values refer to respectively the highest MAP value and FPS value
  2. We control the sizes of the input images under different models to design multiple sets of comparison experiments, and compare the object detection accuracy and speed