(论文阅读18/100)SSD: Single Shot MultiBox Detector

文献阅读笔记

简介

题目

SSD: Single Shot MultiBox Detector

作者

Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, Alexander C. Berg

原文链接

https://arxiv.org/pdf/1512.02325v2.pdf

【精选】目标检测->SSD算法-CSDN博客

关键词

SSD

研究问题

a method for detecting objects in images using a single deep neural network

研究方法

Our approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location.

解决了多尺度问题。

研究结论

SSD easy to train and can straightforward to integrate into systems that require a detection component.

创新不足

可以设置更好的bounding boxes,使其位置和特征比例图上每个位置的感受野更好地对其。

额外知识

Discretize:离散化

Eliminate:排除,消除

Encapsulate:总结

Utilize:利用

Unified:统一

Varients:变体

Prevailed:盛行

Benchmark:基准

Albeit:虽然

Intensive:密集的

High-end hardware:高端硬件

Offset:偏移

High-profile:高知名度的

Bounding box

Default box

Augmentation:扩充

Jaccard overlap:交并比

Aspect ratio:纵横比

Monotonically:单调地

Pruning:修剪

你可能感兴趣的:(论文阅读,python,人工智能,计算机视觉)