Improving Transferability of Representations via Augmentation-Aware Self-Supervision
Accepted to NeurIPS 2021
TL;DR: Learning augmentation-aware information by predicting the difference between two augmented samples improves the transferability of representations.
Dependencies
conda create -n AugSelf python=3.8 pytorch=1.7.1 torchvision=0.8.2 cudatoolkit=10.1 ignite -c pytorch
conda activate AugSelf
pip install scipy tensorboard kornia==0.4.1 sklearn
Checkpoints
We provide ImageNet100-pretrained models in this Dropbox link.
Pretraining
We here provide SimSiam+AugSelf pretraining scripts. For training the baseline (i.e., no AugSelf), remove --ss-crop and --ss-color options. For using other frameworks like SimCLR, use the --framework option.
STL-10
CUDA_VISIBLE_DEVICES=0 python pretrain.py \
--logdir ./logs/stl10/simsiam/aug_self \
--framework simsiam \
--dataset stl10 \
--datadir DATADIR \
--model resnet18 \
--batch-size 256 \
--max-epochs 200 \
--ss-color 1.0 --ss-crop 1.0
ImageNet100
python pretrain.py \
--logdir ./logs/imagenet100/simsiam/aug_self \
--framework simsiam \
--dataset imagenet100 \
--datadir DATADIR \
--batch-size 256 \
--max-epochs 500 \
--model resnet50 \
--base-lr 0.05 --wd 1e-4 \
--ckpt-freq 50 --eval-freq 50 \
--ss-crop 0.5 --ss-color 0.5 \
--num-workers 16 --distributed
Evaluation
Our main evaluation setups are linear evaluation on fine-grained classification datasets (Table 1) and few-shot benchmarks (Table 2).
linear evaluation
CUDA_VISIBLE_DEVICES=0 python transfer_linear_eval.py \
--pretrain-data imagenet100 \
--ckpt CKPT \
--model resnet50 \
--dataset cifar10 \
--datadir DATADIR \
--metric top1
few-shot
CUDA_VISIBLE_DEVICES=0 python transfer_few_shot.py \
--pretrain-data imagenet100 \
--ckpt CKPT \
--model resnet50 \
--dataset cub200 \
--datadir DATADIR
19 Feb 28, 2022
1 Nov 18, 2021
182 Dec 19, 2022
3 Feb 18, 2022
2 Jul 23, 2022
296 Dec 29, 2022
86 Dec 27, 2022
55 Dec 30, 2022
2 Oct 21, 2021
114 Dec 22, 2022
23 Sep 21, 2022
20 Nov 29, 2022
62 Dec 10, 2022
3 Jul 06, 2022
244 Jan 04, 2023
5 Jun 28, 2022
55 Dec 06, 2022
3 Feb 26, 2022
53 Dec 17, 2022
8 May 11, 2022