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

ObjDetApp deploys a pytorch model for object detection

A Simplied Framework of GAN Inversion

This repository is an official implementation of the paper MOTR: End-to-End Multiple-Object Tracking with TRansformer.

Implementation of popular SOTA self-supervised learning algorithms as Fastai Callbacks.

Code for "Multi-Time Attention Networks for Irregularly Sampled Time Series", ICLR 2021.

This repository is a basic Machine Learning train & validation Template (Using PyTorch)

Computationally efficient algorithm that identifies boundary points of a point cloud.

This is the official implementation of the paper "Object Propagation via Inter-Frame Attentions for Temporally Stable Video Instance Segmentation".

Easy-to-use,Modular and Extendible package of deep-learning based CTR models .

ICCV2021 Paper: AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection

The Simplest DCGAN Implementation

This is an open source library implementing hyperbox-based machine learning algorithms

PyTorch implementation of ECCV 2020 paper "Foley Music: Learning to Generate Music from Videos "

In this project I played with mlflow, streamlit and fastapi to create a training and prediction app on digits

An Ensemble of CNN (Python 3.5.1 Tensorflow 1.3 numpy 1.13)

Pytorch-Swin-Unet-V2 - a modified version of Swin Unet based on Swin Transfomer V2

Causal estimators for use with WhyNot

implement of SwiftNet:Real-time Video Object Segmentation

Reference implementation for Structured Prediction with Deep Value Networks

A smaller subset of 10 easily classified classes from Imagenet, and a little more French

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

*ObjDetApp* deploys a pytorch model for object detection

A Simplied Framework of GAN Inversion

This repository is an official implementation of the paper MOTR: End-to-End Multiple-Object Tracking with TRansformer.

Implementation of popular SOTA self-supervised learning algorithms as Fastai Callbacks.

Code for "Multi-Time Attention Networks for Irregularly Sampled Time Series", ICLR 2021.

This repository is a basic Machine Learning train & validation Template (Using PyTorch)

Computationally efficient algorithm that identifies boundary points of a point cloud.

This is the official implementation of the paper "Object Propagation via Inter-Frame Attentions for Temporally Stable Video Instance Segmentation".

Easy-to-use,Modular and Extendible package of deep-learning based CTR models .

ICCV2021 Paper: AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection

The Simplest DCGAN Implementation

This is an open source library implementing hyperbox-based machine learning algorithms

PyTorch implementation of ECCV 2020 paper "Foley Music: Learning to Generate Music from Videos "

In this project I played with mlflow, streamlit and fastapi to create a training and prediction app on digits

An Ensemble of CNN (Python 3.5.1 Tensorflow 1.3 numpy 1.13)

Pytorch-Swin-Unet-V2 - a modified version of Swin Unet based on Swin Transfomer V2

Causal estimators for use with WhyNot

implement of SwiftNet:Real-time Video Object Segmentation

Reference implementation for Structured Prediction with Deep Value Networks

A smaller subset of 10 easily classified classes from Imagenet, and a little more French

ObjDetApp deploys a pytorch model for object detection