[论文笔记]Enhancement of SSD by concatenating feature maps for object detection

论文:Enhancement of SSD by concatenating feature maps for object detection 
论文链接:https://arxiv.org/abs/1705.09587


出发点:虽然深度网络的效果会随着feature map数量的增加而提升,但并不代表简单地增加feature map的数量就能达到更好的效果。本文利用特征金字塔的原理,通过改进特征融合方式,共享分类网络的不同层的权重,充分利用特征,提升了原有的SSD的算法效果。


传统SSD的不足:

1.在SSD中,不同层的feature map都是独立作为分类网络的输入,因此可能出现相同物体被不同大小的框同时检测出来的情况。

2.对小尺寸物体的检测效果比较差。


针对传统SSD的改进:

1.利用分类网络增加不同层之间的feature map的联系,减少重复框的出现。

2.通过增加不同层之间的联系,来增加每一层的feature map的个数,使其可以检测到更多的小尺寸物体。



特征融合方式:

1.采用pooling的方式进行融合。

举例:对于最左边的38*38的feature map,将其做pooling后和左边第二个的19*19的feature map做连接,这样原来的conv7层就有两个19*19的feature map了。然后再对这两个19*19的feature map做pooiling,再和左边第三个的10*10的feature map做连接......

2.采用deconvolution的方式进行融合。

举例:从最右边的1*1的feature map往左边做concate。因为deconvolution是降维,所以是从右到左;而前面的pooling是降维,所以是从左到右。

3.同时采用pooling和deconvolution的方式进行融合。

前两种融合方式的缺点在于,信息的传递都是单向的,这样分类网络不能够利用其他方向的信息。需要注意的是,不同层的feature map的scale不同,因此在对不同层的feature map做连接之前,都会对feature map做一个normalization操作。论文采用第3种特征融合方式。

通过rainbow concatenation,每一层的feature map的个数都会变成2816个(是512, 1024, 512, 256, 256和256的和)。






Object detection in remote sensing images is a challenging task due to the complex backgrounds, diverse object shapes and sizes, and varying imaging conditions. To address these challenges, fine-grained feature enhancement can be employed to improve object detection accuracy. Fine-grained feature enhancement is a technique that extracts and enhances features at multiple scales and resolutions to capture fine details of objects. This technique includes two main steps: feature extraction and feature enhancement. In the feature extraction step, convolutional neural networks (CNNs) are used to extract features from the input image. The extracted features are then fed into a feature enhancement module, which enhances the features by incorporating contextual information and fine-grained details. The feature enhancement module employs a multi-scale feature fusion technique to combine features at different scales and resolutions. This technique helps to capture fine details of objects and improve the accuracy of object detection. To evaluate the effectiveness of fine-grained feature enhancement for object detection in remote sensing images, experiments were conducted on two datasets: the NWPU-RESISC45 dataset and the DOTA dataset. The experimental results demonstrate that fine-grained feature enhancement can significantly improve the accuracy of object detection in remote sensing images. The proposed method outperforms state-of-the-art object detection methods on both datasets. In conclusion, fine-grained feature enhancement is an effective technique to improve the accuracy of object detection in remote sensing images. This technique can be applied to a wide range of applications, such as urban planning, disaster management, and environmental monitoring.
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值