Learning Region Features for Object Detection

被引：45

作者：

Gu, Jiayuan ^{[1
]}

Hu, Han ^{[2
]}

Wang, Liwei ^{[1
,3
]}

Wei, Yichen ^{[2
]}

Dai, Jifeng ^{[2
]}

机构：

[1] Peking Univ, Sch EECS, Key Lab Machine Percept, MOE, Beijing, Peoples R China

[2] Microsoft Res Asia, Beijing, Peoples R China

[3] Peking Univ, Ctr Data Sci, Beijing Inst Big Data Res, Beijing, Peoples R China

来源：

COMPUTER VISION - ECCV 2018, PT XII | 2018年 / 11216卷

关键词：

D O I：

10.1007/978-3-030-01258-8_24

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

While most steps in the modern object detection methods are learnable, the region feature extraction step remains largely hand-crafted, featured by RoI pooling methods. This work proposes a general viewpoint that unifies existing region feature extraction methods and a novel method that is end-to-end learnable. The proposed method removes most heuristic choices and outperforms its RoI pooling counterparts. It moves further towards fully learnable object detection.

引用

页码：392 / 406

页数：15

共 23 条

[1] MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features [J].

Chen, Liang-Chieh ;

Hermans, Alexander ;

Papandreou, George ;

Schroff, Florian ;

Wang, Peng ;

Adam, Hartwig .

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :4013-4022

[2] Deformable Convolutional Networks [J].

Dai, Jifeng ;

Qi, Haozhi ;

Xiong, Yuwen ;

Li, Yi ;

Zhang, Guodong ;

Hu, Han ;

Wei, Yichen .

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, :764-773

[3] Instance-aware Semantic Segmentation via Multi-task Network Cascades [J].

Dai, Jifeng ;

He, Kaiming ;

Sun, Jian .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :3150-3158

[4]

Dai J, 2016, PROCEEDINGS 2016 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL TECHNOLOGY (ICIT), P1796, DOI 10.1109/ICIT.2016.7475036

[5] Scalable Object Detection using Deep Neural Networks [J].

Erhan, Dumitru ;

Szegedy, Christian ;

Toshev, Alexander ;

Anguelov, Dragomir .

2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, :2155-2162

[6]

Girshick R, 2015, PROC ADVNEURAL INF P

[7] Rich feature hierarchies for accurate object detection and semantic segmentation [J].

Girshick, Ross ;

Donahue, Jeff ;

Darrell, Trevor ;

Malik, Jitendra .

2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, :580-587

[8]

He K., 2017, P IEEE INT C COMPUTE, V2017, P2980

[9] Deep Residual Learning for Image Recognition [J].

He, Kaiming ;

Zhang, Xiangyu ;

Ren, Shaoqing ;

Sun, Jian .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778

[10]

He KM, 2014, LECT NOTES COMPUT SC, V8691, P346, DOI [arXiv:1406.4729, 10.1007/978-3-319-10578-9_23]

← 1 2 3 →