2021

PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices

Yu, Guanghua, Chang, Qinyao, Lv, Wenyu et al.

Understand

The better accuracy and efficiency trade-off has been a challenging problem in object detection.

In this work, we are dedicated to studying key optimizations and neural network architecture choices for object detection to improve accuracy and efficiency.
We investigate the applicability of the anchor-free strategy on lightweight object detection models.
We enhance the backbone structure and design the lightweight structure of the neck, which improves the feature extraction ability of the network.

Built on

Imagenet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei · 2009
Earlier work this paper cites.
Microsoft coco: Common objects in context
Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick · 2014
Earlier work this paper cites.
Fast r-cnn
Ross Girshick · 2015
Earlier work this paper cites.
Spatial pyramid pooling in deep convolutional networks for visual recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun · 2015
Earlier work this paper cites.
Faster r-cnn: Towards real-time object detection with region proposal networks
Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun · 2015
Earlier work this paper cites.
Ssd: Single shot multibox detector
Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C Berg · 2016
Earlier work this paper cites.
You only look once: Unified, real-time object detection
Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi · 2016
Earlier work this paper cites.
Feature pyramid networks for object detection
Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie · 2017
Earlier work this paper cites.
Mask r-cnn
Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Girshick · 2017
Earlier work this paper cites.
Yolo9000: better, faster, stronger
Joseph Redmon and Ali Farhadi · 2017
Earlier work this paper cites.
Smash: one-shot model architecture search through hypernetworks
Original
Andrew Brock, Theodore Lim, James M Ritchie, and Nick Weston · 2017
Earlier work this paper cites.
Focal loss for dense object detection
Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár · 2017
Earlier work this paper cites.
Yolov3: An incremental improvement
Original
Joseph Redmon and Ali Farhadi · 2018
Earlier work this paper cites.
Shufflenet v2: Practical guidelines for efficient cnn architecture design
Ningning Ma, Xiangyu Zhang, Hai-Tao Zheng, and Jian Sun · 2018
Earlier work this paper cites.

Similar

Cascade r-cnn: Delving into high quality object detection
Zhaowei Cai and Nuno Vasconcelos · 2018
Cited alongside, same era.
Cornernet: Detecting objects as paired keypoints
Hei Law and Jia Deng · 2018
Cited alongside, same era.
Efficient neural architecture search via parameters sharing
Hieu Pham, Melody Guan, Barret Zoph, Quoc Le, and Jeff Dean · 2018
Cited alongside, same era.
Squeeze-and-excitation networks
Jie Hu, Li Shen, and Gang Sun · 2018
Cited alongside, same era.
Path aggregation network for instance segmentation
Shu Liu, Lu Qi, Haifang Qin, Jianping Shi, and Jiaya Jia · 2018
Cited alongside, same era.
Fcos: Fully convolutional one-stage object detection
Zhi Tian, Chunhua Shen, Hao Chen, and Tong He · 2019
Cited alongside, same era.
Centernet: Keypoint triplets for object detection
Kaiwen Duan, Song Bai, Lingxi Xie, Honggang Qi, Qingming Huang, and Qi Tian · 2019
Cited alongside, same era.
Objects as points
Original
Xingyi Zhou, Dequan Wang, and Philipp Krähenbühl · 2019
Cited alongside, same era.
Searching for mobilenetv3
Andrew Howard, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang, Yukun Zhu, Ruoming Pang, Vijay Vasudevan, et al · 2019
Cited alongside, same era.
Efficientnet: Rethinking model scaling for convolutional neural networks
Mingxing Tan and Quoc Le · 2019
Cited alongside, same era.
Mnasnet: Platform-aware neural architecture search for mobile
Mingxing Tan, Bo Chen, Ruoming Pang, Vijay Vasudevan, Mark Sandler, Andrew Howard, and Quoc V Le · 2019
Cited alongside, same era.
Nas-fpn: Learning scalable feature pyramid architecture for object detection
Golnaz Ghiasi, Tsung-Yi Lin, and Quoc V Le · 2019
Cited alongside, same era.

Then

Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection
Original
Xiang Li, Wenhai Wang, Lijun Wu, Shuo Chen, Xiaolin Hu, Jun Li, Jinhui Tang, and Jian Yang · 2020
Later among the works it cites.
Distance-iou loss: Faster and better learning for bounding box regression
Zhaohui Zheng, Ping Wang, Wei Liu, Jinze Li, Rongguang Ye, and Dongwei Ren · 2020
Later among the works it cites.
Pp-yolo: An effective and efficient implementation of object detector
Original
Xiang Long, Kaipeng Deng, Guanzhong Wang, Yang Zhang, Qingqing Dang, Yuan Gao, Hui Shen, Jianguo Ren, Shumin Han, Errui Ding, and Shilei Wen · 2020
Later among the works it cites.
Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection
Shifeng Zhang, Cheng Chi, Yongqiang Yao, Zhen Lei, and Stan Z Li · 2020
Later among the works it cites.
YOLObile: Real-time object detection on mobile devices via compression-compilation co-design
Yuxuan Cai · 2020
Later among the works it cites.
Ghostnet: More features from cheap operations
Kai Han, Yunhe Wang, Qi Tian, Jianyuan Guo, Chunjing Xu, and Chang Xu · 2020
Later among the works it cites.
ultralytics/yolov5: v6.0 - YOLOv5n ’Nano’ models, Roboflow integration, TensorFlow export, OpenCV DNN support, October 2021
Glenn Jocher, Alex Stoken, Ayush Chaurasia, Jirka Borovec, NanoCode012, TaoXie, Yonghye Kwon, Kalen Michael, Liu Changyu, Jiacong Fang, Abhiram V, Laughing, tkianai, yxNONG, Piotr Skalski, Adam Hogan, Jebastin Nadar, imyhxy, Lorenzo Mammana, AlexWang1900, Cristi Fati, Diego Montes, Jan Hajek, Laurentiu Diaconu, Mai Thanh Minh, Marc, albinxavi, fatih, oleg, and wanghaoyang0106 · 2021
Closest in time.
Yolox: Exceeding yolo series in 2021
Original
Zheng Ge, Songtao Liu, Feng Wang, Zeming Li, and Jian Sun · 2021
Closest in time.
Varifocalnet: An iou-aware dense object detector
Haoyang Zhang, Ying Wang, Feras Dayoub, and Niko Sunderhauf · 2021
Closest in time.
PaddleDetection, object detection and instance segmentation toolkit based on paddlepaddle
PaddlePaddle Authors · 2021
Closest in time.
Pp-yolov2: A practical object detector, 2021
Xin Huang, Xinxin Wang, Wenyu Lv, Xiaying Bai, Xiang Long, Kaipeng Deng, Qingqing Dang, Shumin Han, Qiwen Liu, Xiaoguang Hu, Dianhai Yu, Yanjun Ma, and Osamu Yoshie · 2021
Closest in time.
Mobiledets: Searching for object detection architectures for mobile accelerators
Yunyang Xiong, Hanxiao Liu, Suyog Gupta, Berkin Akin, Gabriel Bender, Yongzhe Wang, Pieter-Jan Kindermans, Mingxing Tan, Vikas Singh, and Bo Chen · 2021
Closest in time.
Pp-lcnet: A lightweight cpu convolutional neural network, 2021
Cheng Cui, Tingquan Gao, Shengyu Wei, Yuning Du, Ruoyu Guo, Shuilong Dong, Bin Lu, Ying Zhou, Xueying Lv, Qiwen Liu, Xiaoguang Hu, Dianhai Yu, and Yanjun Ma · 2021
Closest in time.
Paddle Lite, multi-platform high performance deep learning inference engine
PaddlePaddle Authors · 2021
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…