arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1804.06215cs.CV
收藏

DetNet:用于目标检测的骨干网络

DetNet: A Backbone network for Object Detection

School of Software Tsinghua University(清华大学软件学院);Megvii Inc.(旷视科技有限公司)

Zeming Li, Chao Peng, Gang Yu, Xiangyu Zhang, Yangdong Deng, Jian Sun

摘要:

最近基于CNN的对象检测器,无论是像YOLO、SSD和RetinaNe这样的一阶段方法,还是像Faster R-CNN CNN、R-FCN和FPN这样的两阶段检测器,通常都试图直接从为图像分类设计的ImageNet预训练模型中进行微调。针对目标检测的主干特征提取器的研究还很少。更重要的是,图像分类和目标检测的任务之间存在若干差异。1.最近的对象检测器,如FPN和RetinaNet通常涉及额外的阶段对图像分类的任务,以处理具有各种尺度的对象。2.目标检测不仅需要识别目标实例的类别,而且需要空间定位。较大的下采样因子带来较大的有效感受野,有利于图像分类,但不利于目标定位。由于图像分类和目标检测之间的差距,我们提出了DetNet,这是一种专门为目标检测设计的新型骨干网络。此外,DetNet包括额外的阶段,对传统的骨干网络的图像分类,同时保持高的空间分辨率在更深的层。在基于DetNet~(4.8G FLOPs)主干网的MSCOCO基准测试上,实现了目标检测和实例分割,取得了较好的效果。代码将被发布用于复制。

英文摘要:

Recent CNN based object detectors, no matter one-stage methods like YOLO, SSD, and RetinaNe or two-stage detectors like Faster R-CNN, R-FCN and FPN are usually trying to directly finetune from ImageNet pre-trained models designed for image classification. There has been little work discussing on the backbone feature extractor specifically designed for the object detection. More importantly, there are several differences between the tasks of image classification and object detection. 1. Recent object detectors like FPN and RetinaNet usually involve extra stages against the task of image classification to handle the objects with various scales. 2. Object detection not only needs to recognize the category of the object instances but also spatially locate the position. Large downsampling factor brings large valid receptive field, which is good for image classification but compromises the object location ability. Due to the gap between the image classification and object detection, we propose DetNet in this paper, which is a novel backbone network specifically designed for object detection. Moreover, DetNet includes the extra stages against traditional backbone network for image classification, while maintains high spatial resolution in deeper layers. Without any bells and whistles, state-of-the-art results have been obtained for both object detection and instance segmentation on the MSCOCO benchmark based on our DetNet~(4.8G FLOPs) backbone. The code will be released for the reproduction.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑