2020/06/01 by Mingxing Tan, Ruoming Pang, Quoc V. Le · 82 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Domain Adaptation and Few-Shot Learning
paper · doi:10.1109/cvpr42600.2020.01079
openalex publication_date 2020/06/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/30
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 EfficientDet-D7 achieves state-of-the-art 52.2 AP on COCO test-dev with 52M parameters and 325B FLOPs1, being 4x - 9x smaller and using 13x - 42x fewer FLOPs than previous detector. Code is available at https://github.com/google/ automl/tree/master/efficientdet.