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

2021 CCF BDCI 全国信息检索挑战杯（CCIR-Cup）智能人机交互自然语言理解赛道第二名参赛解决方案

Package for extracting emotions from social media text. Tailored for financial data.

Anchor-free Oriented Proposal Generator for Object Detection

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

Point Cloud Denoising input segmentation output raw point-cloud valid/clear fog rain de-noised Abstract Lidar sensors are frequently used in environme

Code release for paper: The Boombox: Visual Reconstruction from Acoustic Vibrations

PyTorch Implementation of "Light Field Image Super-Resolution with Transformers"

Individual Treatment Effect Estimation

This is the accompanying toolbox for the paper "A Survey on GANs for Anomaly Detection"

TGRNet: A Table Graph Reconstruction Network for Table Structure Recognition

Official PyTorch Implementation of Mask-aware IoU and maYOLACT Detector [BMVC2021]

A library for uncertainty quantification based on PyTorch

an Evolutionary Algorithm assisted GAN

Expand human face editing via Global Direction of StyleCLIP, especially to maintain similarity during editing.

Iowa Project - My second project done at General Assembly, focused on feature engineering and understanding Linear Regression as a concept

This repository stores the code to reproduce the results published in "TiWS-iForest: Isolation Forest in Weakly Supervised and Tiny ML scenarios"

Demo code for ICCV 2021 paper "Sensor-Guided Optical Flow"

Pytorch implementation for "Adversarial Robustness under Long-Tailed Distribution" (CVPR 2021 Oral)

Personalized Federated Learning using Pytorch (pFedMe)

Complete* list of autonomous driving related datasets