Fashion Detection in the Wild (Deep Clothes Detector)

Related tags

Core ML computer-vision deep-learning vision-for-fashion clothes-detection clothes-detector
Overview

Fashion Detection in the Wild (Deep Clothes Detector)

[Project] [Paper]

Overview

Deep Clothes Detector is a clothes detection framework based on Fast R-CNN. Given a fashion image, this software finds and localizes potential upper-body clothes, lower-body clothes and full-body clothes in it, respectively.

Further information please contact Tingwu Wang and Ziwei Liu.

Requirements

Getting started

Place "fashion_detector.caffemodel" into "./models/"
  • Run the testing script:
matlab ./demo.m

Dataset

Large-scale Fashion (DeepFashion) Database

License and Citation

The use of this software is RESTRICTED to non-commercial research and educational purposes.

@inproceedings{liu2016deepfashion,
 author = {Ziwei Liu, Ping Luo, Shi Qiu, Xiaogang Wang, and Xiaoou Tang},
 title = {DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations},
 booktitle = {Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 month = {June},
 year = {2016} 
}
Comments
  • Fashion Net

    Fashion Net

    This does not implement the FashionNet in DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations and doesn't work. Also, the parameters of layers are not well explained in the paper? can't really see how can research community reproduce the results in the paper :(

    opened by ankitkumar8 2
  • Some questions about classification in FashionNet

    Some questions about classification in FashionNet

    hello @liuziwei7, I have been reading your paper Deepfashion. It is a bit confused about the loss function of attribute classification in the paper. The paper says w_pos and w_neg are two coefficients, determined by the ratio of the numbers of positive and negative samples in the dataset. My understanding is like this:

                           w_pos = num_positve / num_dataset
                       w_neg = 1 - w_pos

    Is my understanding wrong? Looking forward to your reply, thank you very much!

    opened by zuoxiang95 0
  • DARN implementation and training strategy

    DARN implementation and training strategy

    Hi authors,

    Can you please explain what was your methodology of training DARN network? DARN has n-branches for each attribute group and expects to have one label per class but in deep fashion data, many a times, multiple attributes belonging to same group get activated (multi-label per class). How are training DARN in that case?

    opened by pbamotra 0
  • The performance on Maxi Dresses doesn't go well

    The performance on Maxi Dresses doesn't go well

    Hi Ziwei,

    Thanks for your excellent idea and code along with the great contribution to the fashion field.

I meet a question after running your code and caffemodel.

It seems that the tests on **Maxi Dress** sets such as on _Painted Floral Maxi Dress_ doesn't goes well.

You can refer to the following figure：

    fashion-detection-error

    Are you doing a further research or having an newer code for upgrading the performance? 

I‘m very interested in this project.   

Thanks!
    opened by Sensenzhl 0
  • How to train the network?

    How to train the network?

    Hello @liuziwei7,

    I had looked through the paper "DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations" but I could not find any experiments about bounding box detection. So I would like to ask something about training facts of your network.

    1. It seems that you used bounding box annotations (not the landmarks ones) and trained the public fast r-cnn (I mean, a non-customized version) with the boxes. Am I on the right track?

    2. Could you explain some details about training/testing data? (1) training data type: only in-shop(or consumer) images or both of them (2) the number of images: training and testing, respectively

    3. Could you share your evaluation methods and results?

    By the way, thanks for your sharing the models and the codes! It is really awesome and helpful!

    opened by salopge 1
Owner
Ziwei Liu
Ziwei Liu
GitHub https://liuziwei7.github.io/projects/DeepFashion.html
Holistically-Nested Edge Detection (HED) using CoreML and Swift

HED-CoreML Holistically-Nested Edge Detection (HED) using CoreML and Swift This is the repo for tutorial, that contains an example application that ru

Andrey Volodin 101 Dec 25, 2022
TextDetection-CoreML - This project is Text Detection on iOS using Vision built-in model

This project is Text Detection on iOS using Vision built-in model. If you are interested in iOS + Machine Learning, visit here yo

tucan9389 61 Nov 17, 2022
Annotation - Generate files to train with Object Detection by Create ML

CreateML Annotation Generate files to train with Object Detection by Create ML.

Vaida 10 Nov 7, 2022
Cheap price detector - Cheap Flight Ticket Price Detector

Cheap Flight Price Detector ✈️ Have you ever searched for flight tickets in a wa

Daniel Grimm 1 Mar 11, 2022
On-device wake word detection powered by deep learning.

Porcupine Made in Vancouver, Canada by Picovoice Porcupine is a highly-accurate and lightweight wake word engine. It enables building always-listening

Picovoice 2.8k Dec 30, 2022
golf pose detection Analyzing golf pose with MLKit pose detection

golf-pose golf pose detection Analyzing golf pose with MLKit pose detection (PHI NETWORKS, 창의적통합설계, 2021) Standard & Frameworks iOS platform (Swift, R

Donghyun Lee 1 Jan 24, 2022
Notches Gone Wild!

Notchmeister Notches Gone Wild! Building First, clone the project. git clone https://github.com/chockenberry/Notchmeister.git You can locally override

Craig Hockenberry 114 Dec 23, 2022
Marshaling the typeless wild west of [String: Any]

Marshal In Swift, we all deal with JSON, plists, and various forms of [String: Any]. Marshal believes you don't need a Ph.D. in monads or magic mirror

Utah iOS and Mac Developers 694 Dec 19, 2022
A simple wrapper for the iOS Keychain to allow you to use it in a similar fashion to User Defaults. Written in Swift.

SwiftKeychainWrapper A simple wrapper for the iOS / tvOS Keychain to allow you to use it in a similar fashion to User Defaults. Written in Swift. Prov

Jason 1.5k Dec 30, 2022
Fashion is your helper to share and reuse UI styles in a Swifty way.

Fashion is your helper to share and reuse UI styles in a Swifty way. The main goal is not to style your native apps in CSS, but use a set

Vadym Markov 124 Nov 20, 2022
A simple wrapper for the iOS Keychain to allow you to use it in a similar fashion to User Defaults. Written in Swift.

SwiftKeychainWrapper A simple wrapper for the iOS / tvOS Keychain to allow you to use it in a similar fashion to User Defaults. Written in Swift. Prov

Jason 1.5k Jan 8, 2023
Simple motion detector for ⌚️ (watchOS) shake gesture.

WatchShaker Simple motion detector for ⌚️ (watchOS) shake gesture. WatchShaker is a watchOS helper to get your ⌚️ shake movements Requirements watchOS

Ezequiel França 200 Dec 22, 2022
NSData Detector with swift

NSDataDetector This playground demonstrates a weird difference in behaviour between Xcodes 12.5.1 and 13.1 regarding NSDataDetector. Try to run it usi

Vinícius Rodrigues de Uzêda 0 Dec 7, 2021
An NSFW image detector for Swift built as an extension on UIImage.

Swift_NSFW_Detector An NSFW image detector for Swift built as an extension on UIImage. If you've ever allowed users to share images you are probably w

Chris Brown 5 Nov 27, 2022
QR code detector. Simple usage, you can get recognition results via delegate or callback.

SPQRCode QR code detector. Simple usage, you can get recognition results via delegate or callback. Installation Swift Package Manager CocoaPods Manual

Sparrow Code 58 Jan 6, 2023
An open source library for building deep-linkable SwiftUI applications with composition, testing and ergonomics in mind

Composable Navigator An open source library for building deep-linkable SwiftUI applications with composition, testing and ergonomics in mind Vanilla S

Bahn-X 539 Jan 8, 2023
Turning on a VPN is always a painful experience on an iOS device due to the deep nested menus.

VPN On Turning on a VPN is always a painful experience on an iOS device due to the deep nested menus. This App installs a Today Widget into Notificati

Lex Tang 4.4k Dec 26, 2022
A splendid route-matching, block-based way to handle your deep links.

DeepLink Kit Overview DeepLink Kit is a splendid route-matching, block-based way to handle your deep links. Rather than decide how to format your URLs

Button 3.4k Dec 30, 2022
Protocol oriented, Cocoa UI abstractions based library that helps to handle view controllers composition, navigation and deep linking tasks in the iOS application. Can be used as the universal replacement for the Coordinator pattern.

RouteComposer RouteComposer is the protocol oriented, Cocoa UI abstractions based library that helps to handle view controllers composition, navigatio

Eugene Kazaev 713 Dec 25, 2022
An open source library for building deep-linkable SwiftUI applications with composition, testing and ergonomics in mind

Composable Navigator An open source library for building deep-linkable SwiftUI applications with composition, testing and ergonomics in mind Vanilla S

Bahn-X 538 Dec 8, 2022