2019

Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection

Zhang, Shifeng, Chi, Cheng, Yao, Yongqiang et al.

Understand

Object detection has been dominated by anchor-based detectors for several years.

Recently, anchor-free detectors have become popular due to the proposal of FPN and Focal Loss.
In this paper, we first point out that the essential difference between anchor-based and anchor-free detection is actually how to define positive and negative training samples, which leads to the performance gap between them.
If they adopt the same definition of positive and negative samples during training, there is no obvious difference in the final performance, no matter regressing from a box or a point.

Built on

Rich feature hierarchies for accurate object detection and semantic segmentation
Ross B. Girshick, Jeff Donahue, Trevor Darrell, and Jitendra Malik · 2014
Earlier work this paper cites.
Microsoft COCO: common objects in context
Tsung-Yi Lin, Michael Maire, Serge J. Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C. Lawrence Zitnick · 2014
Earlier work this paper cites.
Fast R-CNN
Ross B. Girshick · 2015
Earlier work this paper cites.
Densebox: Unifying landmark localization with end to end object detection
Lichao Huang, Yi Yang, Yafeng Deng, and Yinan Yu · 2015
Earlier work this paper cites.
Imagenet large scale visual recognition challenge
Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael S. Bernstein, Alexander C. Berg, and Fei-Fei Li · 2015
Earlier work this paper cites.
Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks
Sean Bell, C. Lawrence Zitnick, Kavita Bala, and Ross B. Girshick · 2016
Earlier work this paper cites.
A unified multi-scale deep convolutional neural network for fast object detection
Zhaowei Cai, Quanfu Fan, Rogério Schmidt Feris, and Nuno Vasconcelos · 2016
Earlier work this paper cites.
R-FCN: object detection via region-based fully convolutional networks
Jifeng Dai, Yi Li, Kaiming He, and Jian Sun · 2016
Earlier work this paper cites.
Deep residual learning for image recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun · 2016
Earlier work this paper cites.
Hypernet: Towards accurate region proposal generation and joint object detection
Tao Kong, Anbang Yao, Yurong Chen, and Fuchun Sun · 2016
Earlier work this paper cites.
SSD: single shot multibox detector
Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott E. Reed, Cheng-Yang Fu, and Alexander C. Berg · 2016
Earlier work this paper cites.
G-CNN: an iterative grid based object detector
Mahyar Najibi, Mohammad Rastegari, and Larry S. Davis · 2016
Earlier work this paper cites.
You only look once: Unified, real-time object detection
Joseph Redmon, Santosh Kumar Divvala, Ross B. Girshick, and Ali Farhadi · 2016
Earlier work this paper cites.
Contextual priming and feedback for faster R-CNN
Abhinav Shrivastava and Abhinav Gupta · 2016
Earlier work this paper cites.
Training region-based object detectors with online hard example mining
Abhinav Shrivastava, Abhinav Gupta, and Ross B. Girshick · 2016
Earlier work this paper cites.
Beyond skip connections: Top-down modulation for object detection
Abhinav Shrivastava, Rahul Sukthankar, Jitendra Malik, and Abhinav Gupta · 2016
Earlier work this paper cites.
Improving object detection with one line of code
Navaneeth Bodla, Bharat Singh, Rama Chellappa, and Larry S. Davis · 2017
Earlier work this paper cites.
Deformable convolutional networks
Jifeng Dai, Haozhi Qi, Yuwen Xiong, Yi Li, Guodong Zhang, Han Hu, and Yichen Wei · 2017
Earlier work this paper cites.
DSSD : Deconvolutional single shot detector
Cheng-Yang Fu, Wei Liu, Ananth Ranga, Ambrish Tyagi, and Alexander C. Berg · 2017
Earlier work this paper cites.
Speed/accuracy trade-offs for modern convolutional object detectors
Jonathan Huang, Vivek Rathod, Chen Sun, Menglong Zhu, Anoop Korattikara, Alireza Fathi, Ian Fischer, Zbigniew Wojna, Yang Song, Sergio Guadarrama, and Kevin Murphy · 2017
Earlier work this paper cites.
RON: reverse connection with objectness prior networks for object detection
Tao Kong, Fuchun Sun, Anbang Yao, Huaping Liu, Ming Lu, and Yurong Chen · 2017
Earlier work this paper cites.
ME R-CNN: multi-expert region-based CNN for object detection
Hyungtae Lee, Sungmin Eum, and Heesung Kwon · 2017
Earlier work this paper cites.
Feature pyramid networks for object detection
Tsung-Yi Lin, Piotr Dollár, Ross B. Girshick, Kaiming He, Bharath Hariharan, and Serge J. Belongie · 2017
Earlier work this paper cites.
Focal loss for dense object detection
Tsung-Yi Lin, Priya Goyal, Ross B. Girshick, Kaiming He, and Piotr Dollár · 2017
Earlier work this paper cites.
YOLO9000: better, faster, stronger
Joseph Redmon and Ali Farhadi · 2017
Earlier work this paper cites.

Similar

Faster R-CNN: towards real-time object detection with region proposal networks
Shaoqing Ren, Kaiming He, Ross B. Girshick, and Jian Sun · 2017
Cited alongside, same era.
DSOD: learning deeply supervised object detectors from scratch
Zhiqiang Shen, Zhuang Liu, Jianguo Li, Yu-Gang Jiang, Yurong Chen, and Xiangyang Xue · 2017
Cited alongside, same era.
A-fast-rcnn: Hard positive generation via adversary for object detection
Xiaolong Wang, Abhinav Shrivastava, and Abhinav Gupta · 2017
Cited alongside, same era.
Aggregated residual transformations for deep neural networks
Saining Xie, Ross B. Girshick, Piotr Dollár, Zhuowen Tu, and Kaiming He · 2017
Cited alongside, same era.
Couplenet: Coupling global structure with local parts for object detection
Yousong Zhu, Chaoyang Zhao, Jinqiao Wang, Xu Zhao, Yi Wu, and Hanqing Lu · 2017
Cited alongside, same era.
SOD-MTGAN: small object detection via multi-task generative adversarial network
Yancheng Bai, Yongqiang Zhang, Mingli Ding, and Bernard Ghanem · 2018
Cited alongside, same era.
Cascade R-CNN: delving into high quality object detection
Zhaowei Cai and Nuno Vasconcelos · 2018
Cited alongside, same era.
Context refinement for object detection
Zhe Chen, Shaoli Huang, and Dacheng Tao · 2018
Cited alongside, same era.
Revisiting RCNN: on awakening the classification power of faster RCNN
Bowen Cheng, Yunchao Wei, Honghui Shi, Rogério Schmidt Feris, Jinjun Xiong, and Thomas S. Huang · 2018
Cited alongside, same era.
Learning region features for object detection
Jiayuan Gu, Han Hu, Liwei Wang, Yichen Wei, and Jifeng Dai · 2018
Cited alongside, same era.
Relation networks for object detection
Han Hu, Jiayuan Gu, Zheng Zhang, Jifeng Dai, and Yichen Wei · 2018
Cited alongside, same era.
Parallel feature pyramid network for object detection
Seung-Wook Kim, Hyong-Keun Kook, Jee-Young Sun, Mun-Cheon Kang, and Sung-Jea Ko · 2018
Cited alongside, same era.

Then

Scratchdet: Exploring to train single-shot object detectors from scratch
Rui Zhu, Shifeng Zhang, Xiaobo Wang, Longyin Wen, Hailin Shi, Liefeng Bo, and Tao Mei · 2018
Later among the works it cites.
Towards accurate one-stage object detection with ap-loss
Kean Chen, Jianguo Li, Weiyao Lin, John See, Ji Wang, Lingyu Duan, Zhibo Chen, Changwei He, and Junni Zou · 2019
Closest in time.
Centernet: Keypoint triplets for object detection
Kaiwen Duan, Song Bai, Lingxi Xie, Honggang Qi, Qingming Huang, and Qi Tian · 2019
Closest in time.
Bounding box regression with uncertainty for accurate object detection
Yihui He, Chenchen Zhu, Jianren Wang, Marios Savvides, and Xiangyu Zhang · 2019
Closest in time.
Foveabox: Beyond anchor-based object detector
Tao Kong, Fuchun Sun, Huaping Liu, Yuning Jiang, and Jianbo Shi · 2019
Closest in time.
Cornernet-lite: Efficient keypoint based object detection
Hei Law, Yun Teng, Olga Russakovsky, and Jia Deng · 2019
Closest in time.
Dynamic anchor feature selection for single-shot object detection
Shuai Li, Lingxiao Yang, Jianqiang Huang, Xian-Sheng Hua, and Lei Zhang · 2019
Closest in time.
Scale-aware trident networks for object detection
Yanghao Li, Yuntao Chen, Naiyan Wang, and Zhaoxiang Zhang · 2019
Closest in time.
High-level semantic feature detection: A new perspective for pedestrian detection
Wei Liu, Shengcai Liao, Weiqiang Ren, Weidong Hu, and Yinan Yu · 2019
Closest in time.
Grid R-CNN
Xin Lu, Buyu Li, Yuxin Yue, Quanquan Li, and Junjie Yan · 2019
Closest in time.
Autofocus: Efficient multi-scale inference
Mahyar Najibi, Bharat Singh, and Larry S. Davis · 2019
Closest in time.
Enriched feature guided refinement network for object detection
Jing Nie, Rao Muhammad Anwer, Hisham Cholakkal, Fahad Shahbaz Khan, Yanwei Pang, and Ling Shao · 2019
Closest in time.
Libra R-CNN: towards balanced learning for object detection
Jiangmiao Pang, Kai Chen, Jianping Shi, Huajun Feng, Wanli Ouyang, and Dahua Lin · 2019
Closest in time.
Thundernet: Towards real-time generic object detection
Zheng Qin, Zeming Li, Zhaoning Zhang, Yiping Bao, Gang Yu, Yuxing Peng, and Jian Sun · 2019
Closest in time.
Generalized intersection over union: A metric and a loss for bounding box regression
Hamid Rezatofighi, Nathan Tsoi, JunYoung Gwak, Amir Sadeghian, Ian D. Reid, and Silvio Savarese · 2019
Closest in time.
Learning to rank proposals for object detection
Zhiyu Tan, Xuecheng Nie, Qi Qian, Nan Li, and Hao Li · 2019
Closest in time.
FCOS: fully convolutional one-stage object detection
Zhi Tian, Chunhua Shen, Hao Chen, and Tong He · 2019
Closest in time.
Region proposal by guided anchoring
Jiaqi Wang, Kai Chen, Shuo Yang, Chen Change Loy, and Dahua Lin · 2019
Closest in time.
Learning rich features at high-speed for single-shot object detection
Tiancai Wang, Rao Muhammad Anwer, Hisham Cholakkal, Fahad Shahbaz Khan, Yanwei Pang, and Ling Shao · 2019
Closest in time.
Reppoints: Point set representation for object detection
Ze Yang, Shaohui Liu, Han Hu, Liwei Wang, and Stephen Lin · 2019
Closest in time.
Freeanchor: Learning to match anchors for visual object detection
Xiaosong Zhang, Fang Wan, Chang Liu, Rongrong Ji, and Qixiang Ye · 2019
Closest in time.
Objects as points
Xingyi Zhou, Dequan Wang, and Philipp Krähenbühl · 2019
Closest in time.
Bottom-up object detection by grouping extreme and center points
Xingyi Zhou, Jiacheng Zhuo, and Philipp Krähenbühl · 2019
Closest in time.
Feature selective anchor-free module for single-shot object detection
Chenchen Zhu, Yihui He, and Marios Savvides · 2019
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…