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*, Zhongqi Miao*, Xiaohang Zhan, Jiayun Wang, Boqing Gong, Stella X. Yu (CUHK & UC Berkeley / ICSI)
in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019, Oral Presentation
Further information please contact Zhongqi Miao and Ziwei Liu.
selfatt
to modulatedatt
so that the attention module can be properly trained in the second stage for Places-LT. ImageNet-LT does not have this problem since the weights are not freezed. We have updated new results using fixed code, which is still better than reported. The weights are also updated. Thanks!Places_LT
dataset. The current results are a little bit higher than reported, even with updated F-measure calculation. One important thing to be considered is that we have unfrozon the model weights for the first stage training of Places-LT
, which means it is not suitable for single-GPU training in most cases (we used 4 1080ti in our implementation). However, for the second stage, since the memory and center loss do not support multi-GPUs currently, please switch back to single-GPU training. Thank you very much!False Positive
calculation in util.py
so that the numbers are normal again. The reported F-measure numbers in the paper might be a little bit higher than actual numbers for all baselines. We will update it as soon as possible. We have updated the new F-measure number in the following table. Thanks.use_fc
in ImageNet-LT stage-1 config to False
. Currently, the results for ImageNet-LT is comparable to reported numbers in the paper (a little bit better), and the reproduced results are updated below. We also found the bug in Places-LT. We will update the code and reproduced results as soon as possible. utils.py
. Update re-implemented ImageNet-LT weights at the end of this page.run_network.py
so the models train properly. Update configuration file for Imagenet-LT stage 1 training so that the results from the paper can be reproduced. NOTE: Places-LT dataset have been updated since the first version. Please download again if you have the first version.
First, please download the ImageNet_2014 and Places_365 (256x256 version).
Please also change the data_root
in main.py
accordingly.
Next, please download ImageNet-LT and Places-LT from here. Please put the downloaded files into the data
directory like this:
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
./logs/caffe_resnet152.pth
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
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
Backbone | Many-Shot | Medium-Shot | Few-Shot | F-Measure | Download |
---|---|---|---|---|---|
ResNet-10 | 44.2 | 35.2 | 17.5 | 44.6 | model |
Backbone | Many-Shot | Medium-Shot | Few-Shot | F-Measure | Download |
---|---|---|---|---|---|
ResNet-152 | 43.7 | 40.2 | 28.0 | 50.0 | model |
The current code was prepared using single GPU. The use of multi-GPU can cause problems except for the first stage of Places-LT
.
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}
}