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

Implementation of "Deep Implicit Templates for 3D Shape Representation"

FAST-RIR: FAST NEURAL DIFFUSE ROOM IMPULSE RESPONSE GENERATOR

Official Code for VideoLT: Large-scale Long-tailed Video Recognition (ICCV 2021)

Implementation for our ICCV 2021 paper: Dual-Camera Super-Resolution with Aligned Attention Modules

A Python package for performing pore network modeling of porous media

Zeyuan Chen, Yangchao Wang, Yang Yang and Dong Liu.

Official Python implementation of the 'Sparse deconvolution'-v0.3.0

Manage the availability of workspaces within Frappe/ ERPNext (sidebar) based on user-roles

Ratatoskr: Worcester Tech's conference scheduling system

Build Low Code Automated Tensorflow, What-IF explainable models in just 3 lines of code.

Code for paper "Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs"

Official implementation for (Show, Attend and Distill: Knowledge Distillation via Attention-based Feature Matching, AAAI-2021)

The code of "Dependency Learning for Legal Judgment Prediction with a Unified Text-to-Text Transformer".

Histocartography is a framework bringing together AI and Digital Pathology

Code for the paper "Functional Regularization for Reinforcement Learning via Learned Fourier Features"

This repository contains the code for TABS, a 3D CNN-Transformer hybrid automated brain tissue segmentation algorithm using T1w structural MRI scans

A short code in python, Enchpyter, is able to encrypt and decrypt words as you determine, of course

Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction

Image Super-Resolution by Neural Texture Transfer

This repository contains all source code, pre-trained models related to the paper "An Empirical Study on GANs with Margin Cosine Loss and Relativistic Discriminator"