READING NOTE: DSSD: Deconvolutional Single Shot Detector
来源:互联网 发布:国家统计局gdp数据 编辑:程序博客网 时间:2024/04/30 20:48
TITLE: DSSD: Deconvolutional Single Shot Detector
AUTHER: Cheng-Yang Fu, Wei Liu, Ananth Ranga, Ambrish Tyagi, Alexander C. Berg
FROM: arXiv:1701.06659
CONTRIBUTIONS
- A combination of a state-of-the-art classifier (Residual-101) with a fast detection framework (SSD) is proposed.
- Deconvolution layers are applied to introduce additional large-scale context in object detection and improve accuracy, especially for small objects.
METHOD
This is a successive work of SSD. Compared with original SSD, DSSD (Deconvolutional Single Shot Detector) adds additional deconvolutional layers and more sophisticated structure for category classifiction and bounding box coordinates regression. As shown in the following figure, the part till blue feature maps is same with original SSD. Then Deconvolution Module and Prediction Module are applied.
Recent works such as Beyond Skip Connections: Top-Down Modulation for Object Detection and Feature Pyramid Networks for Object Detection propose to incorporate fine details into the detection framework using deconvolutional layers and skip connections. DSSD utilizes this idea as well using Deconvolutional Module, shown in the following figure.
Several different structures for Prediction Module are proposed. These structures take the idea from ResNet as illustrated in the following figure.
SOME IDEAS
- Using ResNet-101 and more sophisticated structure for prediction is helpful to improve the performance, but the computation cost is high.
- The idea of using deconvolutional layers to enlarge the feature maps and using skip connections to combine detail features is becoming popular.
- READING NOTE: DSSD: Deconvolutional Single Shot Detector
- DSSD : Deconvolutional Single Shot Detector
- DSSD: Deconvolutional Single Shot Detector 论文笔记
- 论文阅读-《DSSD : Deconvolutional Single Shot Detector》
- DSSD: Deconvolutional Single Shot Detector 论文笔记
- [论文笔记]DSSD : Deconvolutional Single Shot Detector
- READING NOTE: SSD: Single Shot MultiBox Detector
- SSD: Single Shot MultiBox Detector
- SSD: Single Shot MultiBox Detector
- SSD: Single Shot MultiBox Detector
- SSD: Single Shot MultiBox Detector
- SSD: Single Shot MultiBox Detector
- SSD: Single Shot MultiBox Detector
- SSD: Single Shot MultiBox Detector
- SSD: Single Shot MultiBox Detector
- SSD: Single Shot MultiBox Detector
- SSD: Single Shot MultiBox Detector
- SSD: Single Shot MultiBox Detector
- #189. 转啊转
- okHttp 基础及封装
- 【CODEVS】树链剖分板子
- 无锁队列 lock free queue
- 无需序列化,复杂数据传递也如此简单,intent及进程间通信简化
- READING NOTE: DSSD: Deconvolutional Single Shot Detector
- Day01
- BFS(广搜)算法与模板 bfs求最短路
- 滚动条
- lantern官方下载
- 3.7V锂电池供电方案探讨
- java学习基础面向对象之构造方法 五-3
- javascript实现,求一组数的最小公倍数
- android可自动定位到底部的textview