SOTAVerified

NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection

2019-04-16CVPR 2019Code Available0· sign in to hype

Golnaz Ghiasi, Tsung-Yi Lin, Ruoming Pang, Quoc V. Le

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

Current state-of-the-art convolutional architectures for object detection are manually designed. Here we aim to learn a better architecture of feature pyramid network for object detection. We adopt Neural Architecture Search and discover a new feature pyramid architecture in a novel scalable search space covering all cross-scale connections. The discovered architecture, named NAS-FPN, consists of a combination of top-down and bottom-up connections to fuse features across scales. NAS-FPN, combined with various backbone models in the RetinaNet framework, achieves better accuracy and latency tradeoff compared to state-of-the-art object detection models. NAS-FPN improves mobile detection accuracy by 2 AP compared to state-of-the-art SSDLite with MobileNetV2 model in [32] and achieves 48.3 AP which surpasses Mask R-CNN [10] detection accuracy with less computation time.

Tasks

Reproductions