ModaNet: A Large-scale Street Fashion Dataset with Polygon Annotations (2018-07-03T00:00:00.000000Z)

TL;DR

A new database called ModaNet, a large-scale collection of images based on Paperdoll dataset, which allows to measure the performance of state-of-the-art algorithms for object detection, semantic segmentation and polygon prediction on street fashion images in detail.

Abstract

Understanding clothes from a single image would have huge commercial and cultural impacts on modern societies. However, this task remains a challenging computer vision problem due to wide variations in the appearance, style, brand and layering of clothing items. We present a new database called ModaNet, a large-scale collection of images based on Paperdoll dataset. Our dataset provides 55,176 street images, fully annotated with polygons on top of the 1 million weakly annotated street images in Paperdoll. ModaNet aims to provide a technical benchmark to fairly evaluate the progress of applying the latest computer vision techniques that rely on large data for fashion understanding. The rich annotation of the dataset allows to measure the performance of state-of-the-art algorithms for object detection, semantic segmentation and polygon prediction on street fashion images in detail.

Authors

F. Yang

5 papers

Shuai Zheng

4 papers

M. Kiapour

2 papers

TL;DR

Abstract

Authors

References47 items

Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Focal Loss for Dense Object Detection

Annotating Object Instances with a Polygon-RNN

Soft-NMS — Improving Object Detection with One Line of Code

Fully Convolutional Networks for Semantic Segmentation

Deformable Convolutional Networks

Feature Pyramid Networks for Object Detection

ImageNet pre-trained models with batch normalization

Pyramid Scene Parsing Network

Xception: Deep Learning with Depthwise Separable Convolutions

DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations

Deep Learning Markov Random Field for Semantic Segmentation

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

R-FCN: Object Detection via Region-based Fully Convolutional Networks

Training Region-Based Object Detectors with Online Hard Example Mining

Exploring Context with Deep Structured Models for Semantic Segmentation

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

Deep Residual Learning for Image Recognition

SSD: Single Shot MultiBox Detector

Human Parsing with Contextualized Convolutional Neural Network

Where to Buy It: Matching Street Clothing Photos in Online Shops

Multi-Scale Context Aggregation by Dilated Convolutions

You Only Look Once: Unified, Real-Time Object Detection

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Cross-Domain Image Retrieval with a Dual Attribute-Aware Ranking Network

Fast R-CNN

Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation

Deep Human Parsing with Active Template Regression

Fully Connected Deep Structured Networks

Conditional Random Fields as Recurrent Neural Networks

Fashion apparel detection: The role of deep convolutional neural network and pose-dependent priors

Fashion Parsing With Video Context

Very Deep Convolutional Networks for Large-Scale Image Recognition

Simultaneous Detection and Segmentation

Fine-Grained Visual Comparisons with Local Learning

Clothing Co-parsing by Joint Image Segmentation and Labeling

Microsoft COCO: Common Objects in Context

Paper Doll Parsing: Retrieving Similar Styles to Parse Clothing Items

A Deformable Mixture Parsing Model with Parselets

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

Parsing clothing in fashion photographs

Associative hierarchical CRFs for object class image segmentation

ImageNet: A large-scale hierarchical image database

TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation

Multiscale conditional random fields for image labeling

Fashion Parsing With Weak Color-Category Labels

Field of Study

Journal Information

Name

Venue Information

Name

Type

URL

Alternate Names