EfficientDet: Scalable and Efficient Object Detection

Published: 17 July 2020
on channel: ComputerVisionFoundation Videos

4,455

Authors: Mingxing Tan, Ruoming Pang, Quoc V. Le Description: Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and propose several key optimizations to improve efficiency. First, we propose a weighted bi-directional feature pyramid network (BiFPN), which allows easy and fast multi-scale feature fusion. Second, we propose a compound scaling method that uniformly scales the resolution, depth, and width for all backbone, feature network, and box/class prediction networks at the same time. Based on these optimizations and EfficientNet backbones, we have developed a new family of object detectors, called EfficientDet, which consistently achieve much better efficiency than prior art across a wide spectrum of resource constraints. In particular, with single-model and single-scale, our EfficientDetD7 achieves state-of-the-art 52.2 AP on COCO test-dev with 52M parameters and 325B FLOPs, being 4x – 9x smaller and using 13x – 42x fewer FLOPs than previous detector.

On this page of the site you can watch the video online EfficientDet: Scalable and Efficient Object Detection with a duration of hours minute second in good quality, which was uploaded by the user ComputerVisionFoundation Videos 17 July 2020, share the link with friends and acquaintances, this video has already been watched 4,455 times on youtube and it was liked by 42 viewers. Enjoy your viewing!

19,948

158