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

ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

Transformer part of 12th place solution in Riiid! Answer Correctness Prediction

PyTorch Implementation for "ForkGAN with SIngle Rainy NIght Images: Leveraging the RumiGAN to See into the Rainy Night"

AITUS - An atomatic notr maker for CYTUS

Understanding Hyperdimensional Computing for Parallel Single-Pass Learning

Code basis for the paper "Camera Condition Monitoring and Readjustment by means of Noise and Blur" (2021)

Deep Markov Factor Analysis (NeurIPS2021)

NHL 94 AI contests

This project is a loose implementation of paper "Algorithmic Financial Trading with Deep Convolutional Neural Networks: Time Series to Image Conversion Approach"

Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

Pytorch Geometric Tutorials

JAXDL: JAX (Flax) Deep Learning Library

MGFN: Multi-Graph Fusion Networks for Urban Region Embedding was accepted by IJCAI-2022.

Benchmark for evaluating open-ended generation

A PyTorch implementation of the architecture of Mask RCNN

Check out the StyleGAN repo and place it in the same directory hierarchy as the present repo

Efficient face emotion recognition in photos and videos

Implementation of various Vision Transformers I found interesting

Autonomous Driving on Curvy Roads without Reliance on Frenet Frame: A Cartesian-based Trajectory Planning Method

This repository contains the code for: RerrFact model for SciVer shared task