Home

Awesome

Large-Scale Long-Tailed Recognition in an Open World

[Project] [Paper] [Blog]

Overview

Open Long-Tailed Recognition (OLTR) is the author's re-implementation of the long-tail recognizer described in:
"Large-Scale Long-Tailed Recognition in an Open World"
Ziwei Liu<sup>*</sup>Zhongqi Miao<sup>*</sup>Xiaohang ZhanJiayun WangBoqing GongStella X. Yu  (CUHK & UC Berkeley / ICSI)  in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019, Oral Presentation

<img src='./assets/intro.png' width=800>

Further information please contact Zhongqi Miao and Ziwei Liu.

Update notifications

Requirements

Data Preparation

<img src='./assets/dataset.png' width=800>

NOTE: Places-LT dataset have been updated since the first version. Please download again if you have the first version.

data
  |--ImageNet_LT
    |--ImageNet_LT_open
    |--ImageNet_LT_train.txt
    |--ImageNet_LT_test.txt
    |--ImageNet_LT_val.txt
    |--ImageNet_LT_open.txt
  |--Places_LT
    |--Places_LT_open
    |--Places_LT_train.txt
    |--Places_LT_test.txt
    |--Places_LT_val.txt
    |--Places_LT_open.txt

Download Caffe Pre-trained Models for Places_LT Stage_1 Training

Getting Started (Training & Testing)

<img src='./assets/pipeline.png' width=800>

ImageNet-LT

python main.py --config ./config/ImageNet_LT/stage_1.py
python main.py --config ./config/ImageNet_LT/stage_2_meta_embedding.py
python main.py --config ./config/ImageNet_LT/stage_2_meta_embedding.py --test
python main.py --config ./config/ImageNet_LT/stage_2_meta_embedding.py --test_open
python main.py --config ./config/ImageNet_LT/stage_1.py --test

Places-LT

python main.py --config ./config/Places_LT/stage_1.py
python main.py --config ./config/Places_LT/stage_2_meta_embedding.py
python main.py --config ./config/Places_LT/stage_2_meta_embedding.py --test
python main.py --config ./config/Places_LT/stage_2_meta_embedding.py --test_open

Reproduced Benchmarks and Model Zoo (Updated on 03/05/2020)

ImageNet-LT Open-Set Setting

BackboneMany-ShotMedium-ShotFew-ShotF-MeasureDownload
ResNet-1044.235.217.544.6model

Places-LT Open-Set Setting

BackboneMany-ShotMedium-ShotFew-ShotF-MeasureDownload
ResNet-15243.740.228.050.0model

CAUTION

The current code was prepared using single GPU. The use of multi-GPU can cause problems except for the first stage of Places-LT.

License and Citation

The use of this software is released under BSD-3.

@inproceedings{openlongtailrecognition,
  title={Large-Scale Long-Tailed Recognition in an Open World},
  author={Liu, Ziwei and Miao, Zhongqi and Zhan, Xiaohang and Wang, Jiayun and Gong, Boqing and Yu, Stella X.},
  booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019}
}