kanshichao / supervised-deep-feature-embedding

The t-SNE visualization and actual query results of the deep feature embeddings for the paper "Supervised Deep Feature Embedding with Hand Crafted Feature" that has been accepted by the IEEE Transactions on Image Processing.

Supervised-Deep-Feature-Embedding

Introduction

This project is to produce the t-SNE visualization and actual query results of the deep feature embeddings. Mainly for the paper "Supervised Deep Feature Embedding with Hand Crafted Feature" based on the Stanford Online Products test data set and the In-shop Clothes Retrieval test data set.

This paper has been accepted for publication in the IEEE Transactions on Image Processing. All feature embeddings of test data sets and all trained models by our methods will be released soon.

Installiation

1. We test our code based on python 2.7 in ubuntu
2. Install or upgrade sklearn by using the commond "sudo pip install -U scikit-learn"

Download Code

git clone --recursive https://github.com/kanshichao/Supervised-Deep-Feature-Embedding.git

Prerequisites

1. Download datasets according to the links that are given in the data folder
2. Download feature embeddings according to the links that are given in the embeddings folder