NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection
Golnaz Ghiasi,Tsung-Yi Lin,Quoc V. Le +2 more
- 16 Apr 2019
- pp 7036-7045
TL;DR: The adopted Neural Architecture Search is adopted and a new feature pyramid architecture in a novel scalable search space covering all cross-scale connections is discovered, named NAS-FPN, which achieves better accuracy and latency tradeoff compared to state-of-the-art object detection models.
read more
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.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
FedMSA: A Model Selection and Adaptation System for Federated Learning
TL;DR: A model selection and adaptation system for Federated Learning (FedMSA), which includes a hardware-aware model selection algorithm that trades-off model training efficiency and model performance base on FL developers’ expectation is proposed.
Object Detection Based on Swin Deformable Transformer-BiPAFPN-YOLOX
TL;DR: Wang et al. as discussed by the authors proposed a region-based Reconstructed Deformable Self-Attention that shifts attention to important regions for efficient global modeling, which improves the feature extraction ability and convergence speed.
Monitoring-Based Traffic Participant Detection in Urban Mixed Traffic: A Novel Dataset and A Tailored Detector
Wei Zhou,Chen Wang,Jingxin Xia,Zhendong Qian,Yuan Wu +4 more
TL;DR: A novel detector named YOLO SOD is proposed, which embeds a super-resolution feature extraction module and uses knowledge distillation to learn the knowledge how the detector with high-resolution inputs perceives small objects and a novel loss function named S-IoU is designed to enable YOLO SOD to focus more on small objects.
7
M2R-Net: deep network for arbitrary oriented vehicle detection in MiniSAR images
TL;DR: Comparisons with SSD, LRTDet, RFCN, DFPN, CMF-RCNN, R3Det, SCRDet demonstrate that M2R-Net has state-of-the-art detection performance.
6
AirBirds: A Large-scale Challenging Dataset for Bird Strike Prevention in Real-world Airports
TL;DR: AirBirds as discussed by the authors is a large-scale dataset of 118,312 time-series images, where a total of 409,967 bounding boxes of flying birds are manually annotated.
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
U-Net: Convolutional Networks for Biomedical Image Segmentation
Olaf Ronneberger,Philipp Fischer,Thomas Brox +2 more
- 05 Oct 2015
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Densely Connected Convolutional Networks
Gao Huang,Zhuang Liu,Laurens van der Maaten,Kilian Q. Weinberger +3 more
- 21 Jul 2017
TL;DR: DenseNet as mentioned in this paper proposes to connect each layer to every other layer in a feed-forward fashion, which can alleviate the vanishing gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.
SSD: Single Shot MultiBox Detector
Wei Liu,Dragomir Anguelov,Dumitru Erhan,Christian Szegedy,Scott Reed,Cheng-Yang Fu,Alexander C. Berg +6 more
- 08 Oct 2016
TL;DR: The approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location, which makes SSD easy to train and straightforward to integrate into systems that require a detection component.
Feature Pyramid Networks for Object Detection
Tsung-Yi Lin,Piotr Dollár,Ross Girshick,Kaiming He,Bharath Hariharan,Serge Belongie +5 more
- 21 Jul 2017
TL;DR: This paper exploits the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost and achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles.
Related Papers (5)
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
Tsung-Yi Lin,Priya Goyal,Ross Girshick,Kaiming He,Piotr Dollár +4 more
- 07 Aug 2017