NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection
Golnaz Ghiasi, Tsung-Yi Lin, Ruoming Pang, Quoc V. Le
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/open-mmlab/mmdetectionpytorch★ 32,525
- github.com/MS-Mind/MS-Code-08/tree/main/nas-fpnmindspore★ 0
- github.com/mindspore-ai/models/tree/master/research/cv/nas-fpnmindspore★ 0
- github.com/Mind23-2/MindCode-3/tree/main/nas-fpnmindspore★ 0
- github.com/Mind23-2/MindCode-101/tree/main/nasnetmindspore★ 0
- github.com/tensorflow/tpu/tree/master/models/official/detectiontf★ 0
- github.com/2023-MindSpore-4/Code-5/tree/main/nas-fpnmindspore★ 0
- github.com/code-implementation1/Code6/tree/main/nas-fpnmindspore★ 0
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.