Improving Transferability of Representations via Augmentation-Aware Self-Supervision

Last update: Sep 16, 2022

Related tags

Overview

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

Improving Transferability of Representations via Augmentation-Aware Self-Supervision

Related tags

Overview

Improving Transferability of Representations via Augmentation-Aware Self-Supervision

Dependencies

Checkpoints

Pretraining

STL-10

ImageNet100

Evaluation

linear evaluation

few-shot

Owner

hankook

📖 Deep Attentional Guided Image Filtering

Yolo algorithm for detection + centroid tracker to track vehicles

GE2340 project source code without credentials.

Official Pytorch implementation of Meta Internal Learning

The official implementation of the CVPR 2021 paper FAPIS: a Few-shot Anchor-free Part-based Instance Segmenter

Density-aware Single Image De-raining using a Multi-stream Dense Network (CVPR 2018)

Official implementation of "A Unified Objective for Novel Class Discovery", ICCV2021 (Oral)

A texturizer that I just made. Nothing special here.

Discerning Decision-Making Process of Deep Neural Networks with Hierarchical Voting Transformation

Deep learning PyTorch library for time series forecasting, classification, and anomaly detection

Virtual Dance Reality Stage: a feature that offers you to share a stage with another user virtually

CS583: Deep Learning

A hue shift helper for OBS

Unofficial Implementation of MLP-Mixer in TensorFlow

MVFNet: Multi-View Fusion Network for Efficient Video Recognition (AAAI 2021)

《Geo Word Clouds》paper implementation

The codes for the work "Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation"

Implementation of Kalman Filter in Python

Wider-Yolo Kütüphanesi ile Yüz Tespit Uygulamanı Yap

offical implement of our Lifelong Person Re-Identification via Adaptive Knowledge Accumulation in CVPR2021