DSSD

最新推荐文章于 2023-11-27 17:29:48 发布

*Major*

最新推荐文章于 2023-11-27 17:29:48 发布

阅读量589

点赞数

本文链接：https://blog.csdn.net/qq_41375318/article/details/103155282

版权

视频教程：B站、网易云课堂、腾讯课堂
代码地址：Gitee、Github
存储地址：
百度云-提取码：
Google云

DSSD-Model(pytorch版本)

1.一论文导读
2.二论文精读
3.三代码实现
4.四问题思索

《DSSD:Deconvolutional Single Shot Detector》
—基于DSSD的目标检测
作者：Cheng-Yang ,Wei Liu
单位：UNC Chapel、 Amazon Inc
发表会议及时间：CVPR 2017
Submission history
[v1] Mon, 23 Jan 2017 22:33:35 UTC (6,659 KB)

补充：可以尝试通过增加上下文内容(context)，来提高mAP
本文就在反卷积部分增加了context,将高层特征和底层特征相融合

Abstract

The main contribution of this paper is an approach for introducing additional context into state-of-the-art general object detection. To achieve this we first combine a state-of-the-art classifier (Residual-101[14]) with a fast detection framework (SSD[18]).

We then augment SSD+Residual-101 with deconvolution layers to introduce additional large-scale context in object detection and improve accuracy, especially for small objects, calling our resulting system DSSD for deconvolutional single shot detector. While these two contributions are easily described at a high-level, a naive implementation does not succeed.

Instead we show that carefully adding additional stages of learned transformations, specifically a module for feed-forward connections in deconvolution and a new output module, enables this new approach and forms a potential way forward for further detection research.

Results are shown on both PASCAL VOC and COCO detection. Our DSSD with 513×513 input achieves 81.5% mAP on VOC2007 test, 80.0% mAP on VOC2012 test, and 33.2% mAP on COCO, outperforming a state-of-the-art method R-FCN[3] on each dataset