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

Developed an optimized algorithm which finds the most optimal path between 2 points in a 3D Maze using various AI search techniques like BFS, DFS, UCS, Greedy BFS and A*

QRec: A Python Framework for quick implementation of recommender systems (TensorFlow Based)

Space Ship Simulator using python

TC-GNN with Pytorch integration

这是一个利用facenet和retinaface实现人脸识别的库，可以进行在线的人脸识别。

Experiments for Fake News explainability project

Differentiable Neural Computers, Sparse Access Memory and Sparse Differentiable Neural Computers, for Pytorch

Official PyTorch implemention of our paper "Learning to Rectify for Robust Learning with Noisy Labels".

Implementation of CoCa, Contrastive Captioners are Image-Text Foundation Models, in Pytorch

Alpha-Zero - Telegram Group Manager Bot Written In Python Using Pyrogram

Deep learning models for classification of 15 common weeds in the southern U.S. cotton production systems.

LONG-TERM SERIES FORECASTING WITH QUERYSELECTOR – EFFICIENT MODEL OF SPARSEATTENTION

Trustworthy AI related projects

Out-of-distribution detection using the pNML regret. NeurIPS2021

[CVPR 2022 Oral] Crafting Better Contrastive Views for Siamese Representation Learning

SimulLR - PyTorch Implementation of SimulLR

Meandering In Networks of Entities to Reach Verisimilar Answers

Multi-Objective Loss Balancing for Physics-Informed Deep Learning

Image Segmentation and Object Detection in Pytorch

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Semantic Segmentation.