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

Efficient semidefinite bounds for multi-label discrete graphical models.

Official PyTorch implementation of the preprint paper "Stylized Neural Painting", accepted to CVPR 2021.

TGS Salt Identification Challenge

Locally cache assets that are normally streamed in POPULATION: ONE

Bayesian Neural Networks in PyTorch

PyTorch Implementation of the SuRP algorithm by the authors of the AISTATS 2022 paper "An Information-Theoretic Justification for Model Pruning"

Automatically Build Multiple ML Models with a Single Line of Code. Created by Ram Seshadri. Collaborators Welcome. Permission Granted upon Request.

Code for paper Adaptively Aligned Image Captioning via Adaptive Attention Time

Facial detection, landmark tracking and expression transfer library for Windows, Linux and Mac

Repo for "TableParser: Automatic Table Parsing with Weak Supervision from Spreadsheets" at [email protected]

Cluttered MNIST Dataset

A Pose Estimator for Dense Reconstruction with the Structured Light Illumination Sensor

Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration

NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size

EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoising

This repository contains the code for our paper VDA (public in EMNLP2021 main conference)

🥇 LG-AI-Challenge 2022 1위 솔루션 입니다.

Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis

code for the ICLR'22 paper: On Robust Prefix-Tuning for Text Classification

Cancer Drug Response Prediction via a Hybrid Graph Convolutional Network