EfficientDet: Scalable and Efficient Object Detection

CVPR 2020  ·  Mingxing Tan, Ruoming Pang, Quoc V. Le ·

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 multiscale 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 better 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 EfficientDet-D7 achieves state-of-the-art 55.1 AP on COCO test-dev with 77M parameters and 410B FLOPs, being 4x - 9x smaller and using 13x - 42x fewer FLOPs than previous detectors. Code is available at https://github.com/google/automl/tree/master/efficientdet.

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract


Results from the Paper

 Ranked #1 on Object Detection on COCO test-dev (Hardware Burden metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Object Detection COCO minival EfficientDet-D7x (single-scale) AP50 73.4 # 6
AP75 59.0 # 5
APS 40.0 # 5
APM 58.0 # 6
APL 67.9 # 9
Object Detection COCO test-dev EfficientDet-D7x (single-scale) APM 57.9 # 15
Hardware Burden None # 1
Operations per network pass None # 1

Results from Other Papers

Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Object Detection COCO test-dev EfficientDet-D7(single-scale) box AP 53.7 # 33
AP50 72.4 # 17
APM 57.0 # 19
APL 66.3 # 21
Hardware Burden None # 1
Operations per network pass None # 1