数据集: DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations(2016)

最新推荐文章于 2024-08-22 08:29:44 发布

studyeboy

最新推荐文章于 2024-08-22 08:29:44 发布

阅读量227

点赞数

分类专栏：深度学习数据库文章标签：数据集 DeepFashion clothes recognition retrieval

本文链接：https://blog.csdn.net/studyeboy/article/details/115747994

版权

73 篇文章 27 订阅

订阅专栏

3 篇文章 0 订阅

订阅专栏

Motivation

Task: clothes recognition and retrieval(衣服识别和检索)

Data Source（数据源）
Search engines(搜索引擎)， online stores（网上商店）， user posts（用户帖子）.
Quality Control（质量控制）
Duplicate removal（消除重复）, fast screening（快速筛选）, double checking（双重检查）
Annotation Assessment（注释评估）
Sample Images（示例图像）
- Category and Attribute Prediction Benchmark
- In-shop Clothes Retrieval Benchmark
- Consumer-to-shop Clothes Retrieval Benchmark
- Fashion Landmark Detection Benchmark
Attributes Statistics（属性统计）
Landmarks and Pairs

在这里插入图片描述

Network Architecture
FashionNet jointly predicts landmarks and attributes to unify global and local feature learning.
Landmark Pooling Layer
Landmark pooling layer pools and gates features from estimated landmark locations.
Multi-task Learning
Cross-entropy loss for attributes, Euclidean loss for landmarks, triplet loss for pairs.