Towards Universal Object Detection by Domain Attention
Towards Universal Object Detection by Domain Attention
复制标题
DOI：
10.1109/cvpr.2019.00746
复制
发表时间：
2019-04
期刊：
影响因子：
--
通讯作者：
Xudong Wang;Zhaowei Cai;Dashan Gao;N. Vasconcelos
中科院分区：
文献类型：
--
作者：
Xudong Wang;Zhaowei Cai;Dashan Gao;N. Vasconcelos
尽管在视觉识别的通用表示方面的努力越来越多，但很少有人解决对象检测问题。在本文中，我们开发了一个有效的和高效的通用对象检测系统，能够工作在各种图像域，从人脸和交通标志到医学CT图像。与多域模型不同，该通用模型不需要感兴趣域的先验知识。这是通过引入一个新的家庭的适应层，基于挤压和激励的原则，和一个新的域注意力机制。在所提出的通用检测器中，所有参数和计算都是跨域共享的，并且单个网络始终处理所有域。在一个新建立的11个不同数据集的通用对象检测基准上的实验表明，该检测器的性能优于一组单独的检测器、多域检测器和基线通用检测器，其参数比单域基线检测器增加了1.3倍。代码和基准可以在http://www.svcl.ucsd.edu/projects/universal-detection/上获得。
Despite increasing efforts on universal representations for visual recognition, few have addressed object detection. In this paper, we develop an effective and efficient universal object detection system that is capable of working on various image domains, from human faces and traffic signs to medical CT images. Unlike multi-domain models, this universal model does not require prior knowledge of the domain of interest. This is achieved by the introduction of a new family of adaptation layers, based on the principles of squeeze and excitation, and a new domain-attention mechanism. In the proposed universal detector, all parameters and computations are shared across domains, and a single network processes all domains all the time. Experiments, on a newly established universal object detection benchmark of 11 diverse datasets, show that the proposed detector outperforms a bank of individual detectors, a multi-domain detector, and a baseline universal detector, with a 1.3x parameter increase over a single-domain baseline detector. The code and benchmark are available at http://www.svcl.ucsd.edu/projects/universal-detection/.