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

REBEL: Relation Extraction By End-to-end Language generation

Graph neural network message passing reframed as a Transformer with local attention

A curated list of the top 10 computer vision papers in 2021 with video demos, articles, code and paper reference.

A concise but complete implementation of CLIP with various experimental improvements from recent papers

PyTorch implementation of popular datasets and models in remote sensing

Repository accompanying the "Sign Pose-based Transformer for Word-level Sign Language Recognition" paper

Learning Compatible Embeddings, ICCV 2021

kullanışlı ve işinizi kolaylaştıracak bir araç

OrienMask: Real-time Instance Segmentation with Discriminative Orientation Maps

Official Implementation of Neural Splines

Cognate Detection Repository

Learning Skeletal Articulations with Neural Blend Shapes

PyTorch implementation of ARM-Net: Adaptive Relation Modeling Network for Structured Data.

MILK: Machine Learning Toolkit

Official repository for Automated Learning Rate Scheduler for Large-Batch Training (8th ICML Workshop on AutoML)

JstDoS - HTTP Protocol Stack Remote Code Execution Vulnerability

Official Implementation of CoSMo: Content-Style Modulation for Image Retrieval with Text Feedback

Python版OpenCVのTracking APIのサンプルです。DaSiamRPNアルゴリズムまで対応しています。

Federated Deep Reinforcement Learning for the Distributed Control of NextG Wireless Networks.

A simple, fast, and efficient object detector without FPN