mirrors
/
DCL
mirror of https://github.com/JDAI-CV/DCL.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Update README.md

master
Yalong Bai 2019-06-21 18:59:58 +08:00 committed by GitHub
parent 4f8bcef76f
commit eb6ed3c74a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 11 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@ -1,14 +1,24 @@
# Destruction and Construction Learning for Fine-grained Image Recognition
By Yue Chen, Yalong Bai, Wei Zhang, Tao Mei
Speical thanks to [Yuanzhi Liang](https://github.com/akira-l) for code refactoring.
## UPDATE Jun. 21
Our solution for the FGVC Challenge 2019 (The Sixth Workshop on Fine-Grained Visual Categorization in CVPR 2019) is updated!
With ensemble of several DCL based classification models, we won:
- **First Place** in [iMaterialist Challenge on Product Recognition](https://www.kaggle.com/c/imaterialist-product-2019/leaderboard)
- **First Place** in [Fieldguide Challenge: Moths & Butterflies](https://www.kaggle.com/c/fieldguide-challenge-moths-and-butterflies/leaderboard)
- **Second Place** in [iFood - 2019 at FGVC6](https://www.kaggle.com/c/ifood-2019-fgvc6/leaderboard)
## Introduction
This project is a DCL pytorch implementation of [*Destruction and Construction Learning for Fine-grained Image Recognition*](http://openaccess.thecvf.com/content_CVPR_2019/html/Chen_Destruction_and_Construction_Learning_for_Fine-Grained_Image_Recognition_CVPR_2019_paper.html), CVPR2019.
## Requirements
1. Python 3.6