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 1707.01691cs.CV
收藏

RON:反向连接目标先验网络的目标检测

RON: Reverse Connection with Objectness Prior Networks for Object Detection

Tsinghua University(清华大学);Intel Labs China(英特尔中国研究院)

Tao Kong, Fuchun Sun, Anbang Yao, Huaping Liu, Ming Lu, Yurong Chen

摘要:

我们目前的RON,一个有效的通用目标检测的框架。我们的动机是巧妙地将最好的基于区域的(例如,更快的R-CNN)和无区域(例如,SSD)方法。在全卷积架构下,RON主要关注两个基本问题:(a)多尺度对象定位和(b)负样本挖掘。为了解决(a),我们设计了反向连接,这使得网络能够检测CNN多级上的对象。为了处理(b),我们提出了对象优先,以显着减少对象的搜索空间。通过多任务损失函数对反向连接、目标先验和目标检测器进行联合优化,使RON能够直接从不同特征图的所有位置预测最终的检测结果。在具有挑战性的PASCAL VOC 2007、PASCAL VOC 2012和MS COCO基准上进行的大量实验证明了RON的竞争力。具体而言,使用VGG-16和低分辨率384 X384输入大小,网络在PASCAL VOC 2007上获得81.3%的mAP,在PASCAL VOC 2012数据集上获得80.7%的mAP。当数据集变得更大和更困难时,它的优越性会增加,正如MS COCO数据集上的结果所证明的那样。在测试阶段使用1.5G GPU内存,网络速度为15 FPS,比Faster R-CNN对应的速度快3倍。

英文摘要:

We present RON, an efficient and effective framework for generic object detection. Our motivation is to smartly associate the best of the region-based (e.g., Faster R-CNN) and region-free (e.g., SSD) methodologies. Under fully convolutional architecture, RON mainly focuses on two fundamental problems: (a) multi-scale object localization and (b) negative sample mining. To address (a), we design the reverse connection, which enables the network to detect objects on multi-levels of CNNs. To deal with (b), we propose the objectness prior to significantly reduce the searching space of objects. We optimize the reverse connection, objectness prior and object detector jointly by a multi-task loss function, thus RON can directly predict final detection results from all locations of various feature maps. Extensive experiments on the challenging PASCAL VOC 2007, PASCAL VOC 2012 and MS COCO benchmarks demonstrate the competitive performance of RON. Specifically, with VGG-16 and low resolution 384X384 input size, the network gets 81.3% mAP on PASCAL VOC 2007, 80.7% mAP on PASCAL VOC 2012 datasets. Its superiority increases when datasets become larger and more difficult, as demonstrated by the results on the MS COCO dataset. With 1.5G GPU memory at test phase, the speed of the network is 15 FPS, 3X faster than the Faster R-CNN counterpart.

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。

↑