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

(ICONIP 2020) MobileHand: Real-time 3D Hand Shape and Pose Estimation from Color Image

GAN encoders in PyTorch that could match PGGAN, StyleGAN v1/v2, and BigGAN. Code also integrates the implementation of these GANs.

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

Romanian Automatic Speech Recognition from the ROBIN project

Image marine sea litter prediction Shiny

Official Repository for the paper "Improving Baselines in the Wild".

Neurolab is a simple and powerful Neural Network Library for Python

Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition

An NVDA add-on to split screen reader and audio from other programs to different sound channels

An All-MLP solution for Vision, from Google AI

competitions-v2

Flexible Networks for Learning Physical Dynamics of Deformable Objects (2021)

A PyTorch implementation of "Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning", IJCAI-21

Revitalizing CNN Attention via Transformers in Self-Supervised Visual Representation Learning

Official repository for the CVPR 2021 paper "Learning Feature Aggregation for Deep 3D Morphable Models"

Implementation detail for paper "Multi-level colonoscopy malignant tissue detection with adversarial CAC-UNet"

TensorFlow implementation of "TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?"

Multi-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesis (CVPR2022)

Kaggle G2Net Gravitational Wave Detection : 2nd place solution

Automatic meme generation model using Tensorflow Keras.