Detector

Linguistics

Philosophy

Object detection

Telecommunications

Set (abstract data type)

Scalability

Parallel computing

Computer science

Scaling

Code (set theory)

Computer network

FLOPS

Physics

Database

Pattern recognition (psychology)

Mathematics

Optics

Object (grammar)

Feature (linguistics)

Computer engineering

Mathematical analysis

Artificial intelligence

Geometry

Tree (set theory)

Programming language

Backbone network

Pyramid (geometry)

Feature extraction

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.

EfficientDet: Scalable and Efficient Object Detection