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

Pytorch implementation of paper Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data

FinRL-Meta: A Universe for Data-Driven Financial Reinforcement Learning. 🔥

HugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision

(AAAI2022) Style Mixing and Patchwise Prototypical Matching for One-Shot Unsupervised Domain Adaptive Semantic Segmentation

A benchmark dataset for emulating atmospheric radiative transfer in weather and climate models with machine learning (NeurIPS 2021 Datasets and Benchmarks Track)

Deep Learning Interviews book: Hundreds of fully solved job interview questions from a wide range of key topics in AI.

Efficient Speech Processing Tookit for Automatic Speaker Recognition

Improving Object Detection by Label Assignment Distillation

Generating Fractals on Starknet with Cairo

Multi-modal Vision Transformers Excel at Class-agnostic Object Detection

The code for MM2021 paper "Multi-Level Counterfactual Contrast for Visual Commonsense Reasoning"

Unofficial Alias-Free GAN implementation. Based on rosinality's version with expanded training and inference options.

Link prediction using Multiple Order Local Information (MOLI)

Multi Agent Reinforcement Learning for ROS in 2D Simulation Environments

The implementation of the paper "A Deep Feature Aggregation Network for Accurate Indoor Camera Localization".

clDice - a Novel Topology-Preserving Loss Function for Tubular Structure Segmentation

SAPIEN Manipulation Skill Benchmark

Robust and Accurate Object Detection via Self-Knowledge Distillation

The official repository for Deep Image Matting with Flexible Guidance Input

Predicting Event Memorability from Contextual Visual Semantics

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

Pytorch implementation of paper Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data

FinRL­-Meta: A Universe for Data­-Driven Financial Reinforcement Learning. 🔥

HugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision

(AAAI2022) Style Mixing and Patchwise Prototypical Matching for One-Shot Unsupervised Domain Adaptive Semantic Segmentation

A benchmark dataset for emulating atmospheric radiative transfer in weather and climate models with machine learning (NeurIPS 2021 Datasets and Benchmarks Track)

Deep Learning Interviews book: Hundreds of fully solved job interview questions from a wide range of key topics in AI.

Efficient Speech Processing Tookit for Automatic Speaker Recognition

Improving Object Detection by Label Assignment Distillation

Generating Fractals on Starknet with Cairo

Multi-modal Vision Transformers Excel at Class-agnostic Object Detection

The code for MM2021 paper "Multi-Level Counterfactual Contrast for Visual Commonsense Reasoning"

Unofficial Alias-Free GAN implementation. Based on rosinality's version with expanded training and inference options.

Link prediction using Multiple Order Local Information (MOLI)

Multi Agent Reinforcement Learning for ROS in 2D Simulation Environments

The implementation of the paper "A Deep Feature Aggregation Network for Accurate Indoor Camera Localization".

clDice - a Novel Topology-Preserving Loss Function for Tubular Structure Segmentation

SAPIEN Manipulation Skill Benchmark

Robust and Accurate Object Detection via Self-Knowledge Distillation

The official repository for Deep Image Matting with Flexible Guidance Input

Predicting Event Memorability from Contextual Visual Semantics

FinRL-Meta: A Universe for Data-Driven Financial Reinforcement Learning. 🔥