Semantic Scholar Open Access 2019 6702 sitasi

EfficientDet: Scalable and Efficient Object Detection

Mingxing Tan Ruoming Pang Quoc V. Le

Lihat Sumber DOI

Abstrak

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.

Topik & Kata Kunci

Computer Science Engineering

Penulis (3)

Mingxing Tan

Ruoming Pang

Quoc V. Le

Format Sitasi

APA MLA BibTeX

Tan, M., Pang, R., Le, Q.V. (2019). EfficientDet: Scalable and Efficient Object Detection. https://doi.org/10.1109/cvpr42600.2020.01079

Akses Cepat

Lihat di Sumber doi.org/10.1109/cvpr42600.2020.01079

Informasi Jurnal

Tahun Terbit: 2019
Bahasa: en
Total Sitasi: 6702×
Sumber Database: Semantic Scholar
DOI: 10.1109/cvpr42600.2020.01079
Akses: Open Access ✓