graviti
产品服务
解决方案
知识库
公开数据集
关于我们
iMat - Fashion
2D Polygon
许可协议: Public Domain

Overview

Visual analysis of clothing is a topic that has received increasing attention in recent years. Being able to recognize apparel products and associated attributes from pictures could enhance shopping experience for consumers, and increase work efficiency for fashion professionals.

We present a new clothing dataset with the goal of introducing a novel fine-grained segmentation task by joining forces between the fashion and computer vision communities. The proposed task unifies both categorization and segmentation of rich and complete apparel attributes, an important step toward real-world applications.

While early work in computer vision addressed related clothing recognition tasks, these are not designed with fashion insiders’ needs in mind, possibly due to the research gap in fashion design and computer vision. To address this, we first propose a fashion taxonomy built by fashion experts, informed by product description from the internet. To capture the complex structure of fashion objects and ambiguity in descriptions obtained from crawling the web, our standardized taxonomy contains 46 apparel objects (27 main apparel items and 19 apparel parts), and 92 related fine-grained attributes. Secondly, a total of around 50K clothing images (10K with both segmentation and fine-grained attributes, 40K with apparel instance segmentation) in daily-life, celebrity events, and online shopping are labeled by both domain experts and crowd workers for fine-grained segmentation.

In this competition, we challenge you to develop algorithms that will help with an important step towards automatic product detection – to accurately assign segmentations and attribute labels for fashion images. Individuals/Teams with top submissions will be invited to present their work live at the FGVC6 workshop.

数据概要
数据格式
image,
数据量
50K
文件大小
--
| 数据量 50K | 大小 --
iMat - Fashion
2D Polygon
许可协议: Public Domain

Overview

Visual analysis of clothing is a topic that has received increasing attention in recent years. Being able to recognize apparel products and associated attributes from pictures could enhance shopping experience for consumers, and increase work efficiency for fashion professionals.

We present a new clothing dataset with the goal of introducing a novel fine-grained segmentation task by joining forces between the fashion and computer vision communities. The proposed task unifies both categorization and segmentation of rich and complete apparel attributes, an important step toward real-world applications.

While early work in computer vision addressed related clothing recognition tasks, these are not designed with fashion insiders’ needs in mind, possibly due to the research gap in fashion design and computer vision. To address this, we first propose a fashion taxonomy built by fashion experts, informed by product description from the internet. To capture the complex structure of fashion objects and ambiguity in descriptions obtained from crawling the web, our standardized taxonomy contains 46 apparel objects (27 main apparel items and 19 apparel parts), and 92 related fine-grained attributes. Secondly, a total of around 50K clothing images (10K with both segmentation and fine-grained attributes, 40K with apparel instance segmentation) in daily-life, celebrity events, and online shopping are labeled by both domain experts and crowd workers for fine-grained segmentation.

In this competition, we challenge you to develop algorithms that will help with an important step towards automatic product detection – to accurately assign segmentations and attribute labels for fashion images. Individuals/Teams with top submissions will be invited to present their work live at the FGVC6 workshop.

0
立即开始构建AI
graviti
wechat-QR
长按保存识别二维码,关注Graviti公众号

Copyright@Graviti
沪ICP备19019574号
沪公网安备 31011002004865号