ICCV2017: Unlabeled Samples Generated by GAN Improve the Person Re-Identification Baseline in Vitro
来源:互联网 发布:快意电梯营销网络 编辑:程序博客网 时间:2024/05/29 11:43
- 作者:Zhedong Zheng
摘要
提出一个simple的semi-supervised pipline. 该方法只使用训练集而不需要额外的数据。该方法的主要挑战:
- (1)如何仅从训练集获取更多的训练数据,
- (2)如何使用新产生的数据。
本文提出用generative adversarial network(GAN)产生无标签数据,提出label smoothing regulization for outliers(LSRO) (如果训练集的类别数是k, 则该无标签数据属于任意的的概率都是1/K). 用这个方法提高了baselien.
- (3)网络结构:deep convolutional generative adversaria network (DCGAN)+CNN.
- (4)Experiments: Market-1501, CUHK03, Duke.
网络结构
数据集的情况
- Duke
是一个新引入的多目标多视角的行人跟踪数据集。原始的数据集包含来自8个视角的85分钟的高清晰视频。有手工提取得bounding box提供。 本文用了一个子集进行image-based re-ID, 和Maket-1501的格式一样。从视频中每120帧提取一次,一共产生了36411 bounding box(标记【26】)。 用于re-ID的 Duke数据集有来自8个视角的1812个行人。 有1404人同时出现在两个以上的视角中。有408个只出现在一个视角中。 本文,选取702 IDs作为训练集,其余702 IDs作为测试集。 最终,训练集:16,522 images, 702 IDs 测试集:2,228 查询图像,17,661的gallery , 702 IDs
GAN产生的图片
LSRO
阅读全文
0 0
- ICCV2017: Unlabeled Samples Generated by GAN Improve the Person Re-Identification Baseline in Vitro
- [paper note] Human-In-The-Loop Person Re-Identification
- 论文笔记之---Person Re-identification in the Wild
- 【Person Re-ID】In Defense of the Triplet Loss for Person Re-Identification
- Person Re-Identification by Iterative Re-Weighted Sparse Ranking
- 【论文笔记】In Defense of the Triplet Loss for Person Re-Identification
- Person Re-identification Datasets
- Person Re-identification Datasets
- Person Re-identification Overview
- Person Re-identification Overview
- Person Re-identification Datasets
- Multiple People Tracking by Lifted Multicut and Person Re-identification
- Multiple People Tracking by Lifted Multicut and Person Re-identification
- Re-ID: Person Re-identification by Local Maximal Occurrence Representation and Metric Learning 论文解析
- Re-ID:AlignedReID: Surpassing Human-Level Performance in Person Re-Identification 论文解析
- 【Person Re-ID】Person Re-identification: Past, Present and Future
- Person re-identification by Local Maximal Occurrence representation and metric learning
- paper reading——《Improving Person Re-identification by Attribute and Identity Learning》
- 《c语言程序设计》例 2-8 2-9 2-10 2-11
- Gson 解析数组数组时
- springboot 快速集成的一些启动类模块
- 关于SimpleDateFormat安全的时间格式化线程安全问题
- Qt 学习 第6节 添加绘图控件Qwt
- ICCV2017: Unlabeled Samples Generated by GAN Improve the Person Re-Identification Baseline in Vitro
- openCV学习笔记(1)
- opencv-模板匹配
- 获取指定字符的方法
- python: copy库 与 list拷贝
- Diffie-Hellman密钥交换算法
- Java获取Properties文件中值的方法
- Java实战有感02
- Android activity生命周期----电源键关开