Transcription of EfficientDet: Scalable and Efficient Object Detection
{{id}} {{{paragraph}}}
Example: stock market
EfficientDet: Scalable and Efficient Object Detection
EfficientDet: Scalable and Efficient Object DetectionMingxing Tan Ruoming Pang Quoc V. LeGoogle Research, Brain Team{tanmingxing, rpang, efficiency has become increasingly important incomputer vision. In this paper, we systematically study neu-ral network architecture design choices for Object detec-tion and propose several key optimizations to improve ef-ficiency. First, we propose a weighted bi-directional fea-ture pyramid network (BiFPN), which allows easy and fastmulti-scale feature fusion; Second, we propose a compoundscaling method that uniformly scales the resolution, depth,and width for all backbone, feature network, and box/classprediction networks at the same time. Based on these op-timizations and EfficientNet backbones, we have developeda new family of Object detectors, called EfficientDet, whichconsistently achieve much better efficiency than prior artacross a wide spectrum of resource constraints.}
YOLOv3 [31], 30x fewer FLOPs than RetinaNet [21], and 19x fewer FLOPs than the recent ResNet based NAS-FPN [8]. In particular, with single-model and single test-time scale, ourEfficientDet-D7achievesstate-of-the-art52.2AP with 52Mparameters and 325BFLOPs, outperforming pre-vious best detector [42] with 1.5 AP while being 4x smaller
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: