EfficientDet: Scalable and Efficient Object Detection

TLDR

Model efficiency has become increasingly important in computer vision. The paper systematically studies neural network architecture design choices for object detection and proposes key optimizations to improve efficiency. The authors introduce a weighted bi‑directional feature pyramid network (BiFPN) for fast multi‑scale feature fusion and a compound scaling method that uniformly scales resolution, depth, and width across backbone, feature network, and prediction heads, leading to the EfficientDet family of detectors. EfficientDet‑D7 attains 52.2 AP on COCO test‑dev with 52 M parameters and 325 B FLOPs, outperforming prior detectors by being 4–9× smaller and using 13–42× fewer FLOPs. Code is available at https://github.com/google/automl/tree/master/efficientdet.

Abstract

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.