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

A self-supervised 3D representation learning framework named viewpoint bottleneck.

[CVPR 2021] Few-shot 3D Point Cloud Semantic Segmentation

Unified API to facilitate usage of pre-trained "perceptor" models, a la CLIP

[ICCV21] Self-Calibrating Neural Radiance Fields

moving object detection for satellite videos.

CTRMs: Learning to Construct Cooperative Timed Roadmaps for Multi-agent Path Planning in Continuous Spaces

PyTorch code to run synthetic experiments.

Implementation of Axial attention - attending to multi-dimensional data efficiently

DiffStride: Learning strides in convolutional neural networks

AI-UPV at IberLEF-2021 EXIST task: Sexism Prediction in Spanish and English Tweets Using Monolingual and Multilingual BERT and Ensemble Models

A research toolkit for particle swarm optimization in Python

A Pytorch Implementation of [Source data‐free domain adaptation of object detector through domain

A Python package for performing pore network modeling of porous media

Official repository of "Investigating Tradeoffs in Real-World Video Super-Resolution"

D2Go is a toolkit for efficient deep learning

An open software package to develop BCI based brain and cognitive computing technology for recognizing user's intention using deep learning

ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels

PyTorch code for 'Efficient Single Image Super-Resolution Using Dual Path Connections with Multiple Scale Learning'

[CVPR 2022] Pytorch implementation of "Templates for 3D Object Pose Estimation Revisited: Generalization to New objects and Robustness to Occlusions" paper

This project is the PyTorch implementation of our CVPR 2022 paper: