当前位置: X-MOL 学术IEEE Trans. Image Process. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Improving Single Shot Object Detection With Feature Scale Unmixing
IEEE Transactions on Image Processing ( IF 10.6 ) Pub Date : 2021-01-08 , DOI: 10.1109/tip.2020.3048630
Yazhao Li , Yanwei Pang , Jiale Cao , Jianbing Shen , Ling Shao

Due to the advantages of real-time detection and improved performance, single-shot detectors have gained great attention recently. To solve the complex scale variations, single-shot detectors make scale-aware predictions based on multiple pyramid layers. Typically, small objects are detected on shallow layers while large objects are detected on deep layers. However, the features in the pyramid are not scale-aware enough, which limits the detection performance. Two common problems in single-shot detectors caused by object scale variations can be observed: (1) false negative problem, i.e. , small objects are easily missed due to the weak features; (2) part-false positive problem, i.e. , the salient part of a large object is sometimes detected as an object. With this observation, a new Neighbor Erasing and Transferring (NET) mechanism is proposed for feature scale-unmixing to explore scale-aware features in this paper. In NET, a Neighbor Erasing Module (NEM) is designed to erase the salient features of large objects and emphasize the features of small objects in shallow layers. A Neighbor Transferring Module (NTM) is introduced to transfer the erased features and highlight large objects in deep layers. With this mechanism, a single-shot network called NETNet is constructed for scale-aware object detection. In addition, we propose to aggregate nearest neighboring pyramid features to enhance our NET. Experiments on MS COCO dataset and UAVDT dataset demonstrate the effectiveness of our method. NETNet obtains 38.5% AP at a speed of 27 FPS and 32.0% AP at a speed of 55 FPS on MS COCO dataset. As a result, NETNet achieves a better trade-off for real-time and accurate object detection.

中文翻译:

通过特征尺度分解改进单发物体检测

由于实时检测和改进的性能的优点,单发检测器最近引起了极大的关注。为了解决复杂的标度变化,单发检测器基于多个金字塔层进行标度感知预测。通常,在浅层上检测到小物体,而在深层上检测到大物体。但是,金字塔中的特征无法充分感知规模,这限制了检测性能。可以观察到由物体尺度变化引起的单发检测器中的两个常见问题:(1)假阴性问题,IE ,由于功能弱,容易遗漏小物件;(2)部分误报问题,IE ,有时会将大对象的显着部分检测为对象。基于这种观察,提出了一种新的邻居擦除和传输(NET)机制,用于特征尺度分解,以探索本文中可感知尺度的特征。在NET中,邻居擦除模块(NEM)旨在擦除大型对象的显着特征并强调浅层中小型对象的特征。引入了邻居传输模块(NTM),以传输已擦除的功能并突出显示深层中的大对象。通过这种机制,构建了一个称为NETNet的单发网络,用于可感知规模的对象检测。此外,我们建议汇总最近邻的金字塔特征,以增强我们的网络。在MS COCO数据集和UAVDT数据集上的实验证明了我们方法的有效性。NETNet获得38。在MS COCO数据集上,速度为27 FPS的5%的AP和速度为55 FPS的32.0%的AP。因此,NETNet可以更好地权衡实时和精确的对象检测。
更新日期:2021-02-12
down
wechat
bug