An increasing need of running Convolutional Neural Network (CNN) models on mobile devices with limited computing power and memory resource encourages studies on efficient model design. A number of efficient architectures have been proposed in recent years, for example, MobileNet, ShuffleNet, and MobileNetV2. However, all these models are heavily dependent on depthwise separable convolution which lacks efficient implementation in most deep learning frameworks. In this study, we propose an efficient architecture named PeleeNet, which is built with conventional convolution instead.

The paper address the problem of accurate object detection on mobile device which an important problem has not been solved. Current accurate detectors rely on large and deep networks which only be inferred on a GPU. To address this problem, it proposes a SSD based detection method based on a new network termed as Pelee. Pros: The Pelee detector achieves 76.4% mAP on PASCAL VOC2007 and 22.4 mAP on MS COCO dataset at the speed of 17.1 FPS on iPhone 6s and 23.6 FPS on iPhone 8. The accuracies are getting very close to the SSD detectors with VGGNets.