問題：目前的目標檢測器只能適用於單一的檢測場景。
目的：建立一種適用於各種場景的通用的目標檢測系統。
（a）單域檢測器組 （b）自適應多域檢測器 （c）通用檢測器 （d）域注意通用檢測器
相關研究：
目標檢測：兩階段檢測框架：RCNN,Fast R-CNN,Faster R-CNN；一階段檢測框架（速度快）：YOLO,SSD。它們應用在不同數據集上時都需要微調模型。
多任務學習：多任務學習研究如何在一個輸入域內同時學習多個任務。
多域學習/適應：多域學習在已知先驗知識時，解決多個域的表示學習問題。
注意模型：提到了SE模塊。
建立11個數據集通用的目標檢測標準：(1)Pascal VOC:Mark Everingham, SM Ali Eslami, Luc Van Gool, Christo- pher KI Williams, John Winn, and Andrew Zisserman. The pascal visual object classes challenge: A retrospective. Inter- national journal ofcomputer vision, 111(1):98–136, 2015.(2)WiderFace:Shuo Yang, Ping Luo, Chen-Change Loy, and Xiaoou Tang. Wider face: A face detection benchmark. In CVPR, pages 5525–5533, 2016.(3)KITTI:Andreas Geiger, Philip Lenz, and Raquel Urtasun. Are we ready for autonomous driving? the kitti vision benchmark suite. In CVPR, pages 3354–3361, 2012.(4)LISA:Andreas Møgelmose, Mohan M Trivedi, and Thomas B Moeslund. Vision-based traffic sign detection and analy- sis for intelligent driver assistance systems: Perspectives and survey. IEEE Trans. Intelligent Transportation Systems, 13(4):1484–1497, 2012.(5)DOTA:Gui-Song Xia, Xiang Bai, Jian Ding, Zhen Zhu, Serge Be- longie, Jiebo Luo, Mihai Datcu, Marcello Pelillo, and Liang- pei Zhang. Dota: A large-scale dataset for object detection in aerial images. In Proc. CVPR, 2018.(6)COCO:Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll´ar, and C Lawrence Zitnick. Microsoft coco: Common objects in context. In ECCV, pages 740–755, 2014.(7)Watercolor:Naoto Inoue, Ryosuke Furuta, Toshihiko Yamasaki, and Kiy- oharu Aizawa. Cross-domain weakly-supervised object de- tection through progressive domain adaptation. In CVPR, pages 5001–5009, 2018.(8)Clipart:Naoto Inoue, Ryosuke Furuta, Toshihiko Yamasaki, and Kiy- oharu Aizawa. Cross-domain weakly-supervised object de- tection through progressive domain adaptation. In CVPR, pages 5001–5009, 2018.(9)Comic:Naoto Inoue, Ryosuke Furuta, Toshihiko Yamasaki, and Kiy- oharu Aizawa. Cross-domain weakly-supervised object de- tection through progressive domain adaptation. In CVPR, pages 5001–5009, 2018.(10)Kitchen:Georgios Georgakis, Md Alimoor Reza, Arsalan Mousavian, Phi-Hung Le, and Jana Kosecka. Multiview rgb-d dataset for object instance detection. arXiv preprint arXiv:1609.07826, 2016.(11)DeepLesions:Ke Yan, Xiaosong Wang, Le Lu, Ling Zhang, Adam Har- rison, Mohammadhadi Bagheri, and Ronald M Summers. Deep lesion graphs in the wild: relationship learning and organization of significant radiology image findings in a di- verse large-scale lesion database. In IEEE CVPR, 2018.
自適應多域檢測器：
前面的參數是共享的，全連接層做成開關型應用於不同的域（但是需要用到感興趣區域的先驗知識）。
通用檢測器（通用SE適配器組+域注意）：
所有的任務共享一個檢測器， 輸出層會針對不同的域。也就是說除了輸出層，所有的參數都是共享的。
補充（SE）：
