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

Birthday-problem - The birthday problem asks for the probability that, in a set of n randomly chosen people, at least two will share a birthday

Code/data of the paper "Hand-Object Contact Prediction via Motion-Based Pseudo-Labeling and Guided Progressive Label Correction" (BMVC2021)

Code image classification of MNIST dataset using different architectures: simple linear NN, autoencoder, and highway network

Megaverse is a new 3D simulation platform for reinforcement learning and embodied AI research

CV backbones including GhostNet, TinyNet and TNT, developed by Huawei Noah's Ark Lab.

Package for working with hypernetworks in PyTorch.

Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators

Here we present the implementation in TensorFlow of our work about liver lesion segmentation accepted in the Machine Learning 4 Health Workshop

Code for NeurIPS 2020 article "Contrastive learning of global and local features for medical image segmentation with limited annotations"

SAAVN - Sound Adversarial Audio-Visual Navigation,ICLR2022 (In PyTorch)

Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification (NeurIPS 2021)

Facebook AI Image Similarity Challenge: Descriptor Track

[NeurIPS 2020] Blind Video Temporal Consistency via Deep Video Prior

The Video-based Accident Detection System built in Python

Small repo describing how to use Hugging Face's Wav2Vec2 with PyCTCDecode

Python library for computer vision labeling tasks. The core functionality is to translate bounding box annotations between different formats-for example, from coco to yolo.

DP-CL(Continual Learning with Differential Privacy)

EMNLP'2021: Simple Entity-centric Questions Challenge Dense Retrievers

Fast, flexible and fun neural networks.

This repository is maintained for the scientific paper tittled " Study of keyword extraction techniques for Electric Double Layer Capacitor domain using text similarity indexes: An experimental analysis "