Learning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognition (ECCVW 2020)
Taeoh Kim*1, Hyeongmin Lee*1, MyeongAh Cho*1, HoSeong Lee2, Dong Heon Cho2, Sangyoun Lee1
* indicates equal contribution
1 Yonsei University
2 Cognex Deep Learning Lab
Official PyTorch implementation of our paper which has been accepted to 1st Visual Inductive Priors for Data-Efficient Deep Learning Workshop at ECCV 2020 as Oral Presentation.
- PyTorch 1.4.0
- opencv-python
- PIL (pillow)
- tqdm
-
Download UCF-101 training data from UCF-101 dataset.
-
Modify training data using VIPriors Challenge Split.
-
Run train.py with following command. (SlowFast-50 Baseline)
python train.py --dir_data [DB] --out_dir [ExpName] --is_validate
-
Train on RandAugment-T
python train.py --dir_data [DB] --out_dir [ExpName] --is_validate --rand_augmentation --aug_mode randaug --randaug_n [N] --randaug_m [M]
-
Train on Mixing Data Augmentations (cutmix, framecutmix, cubecutmix, mixup, fademixup, cutmixup, framecutmixup, cubecutmixup)
python train.py --dir_data [DB] --out_dir [ExpName] --is_validate --mix_type [Mix_type]
- Run train.py with following command.
python train.py --dir_data [DB] --out_dir [ExpName] --load [ckpt] --test_only --is_validate
If you find the code helpful in your resarch or work, please cite the following paper.
@inproceedings{kim2020learning,
title={Learning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognition},
author={Kim, Taeoh and Lee, Hyeongmin and Cho, MyeongAh and Lee, Ho Seong and Cho, Dong Heon and Lee, Sangyoun},
booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
year={2020}
}