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

Publication describing 3 ML examples at NSLS-II and interfacing into Bluesky

Material del curso IIC2233 Programación Avanzada 📚

Implementation of ProteinBERT in Pytorch

This repository contains the code for using the H3DS dataset introduced in H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction

:boar: :bear: Deep Learning based Python Library for Stock Market Prediction and Modelling

A Python Package for Convex Regression and Frontier Estimation

PyTorch code for ICPR 2020 paper Future Urban Scene Generation Through Vehicle Synthesis

CSE-519---Project - Job Title Analysis (Project for CSE 519 - Data Science Fundamentals)

Bounding Wasserstein distance with couplings

Just playing with getting CLIP Guided Diffusion running locally, rather than having to use colab.

docTR by Mindee (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

PyTorch implementation of "Simple and Deep Graph Convolutional Networks"

Duke Machine Learning Winter School: Computer Vision 2022

The codes for the work "Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation"

A rule-based log analyzer & filter

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with ONNX, TensorRT, ncnn, and OpenVINO supported.

A series of Jupyter notebooks with Chinese comment that walk you through the fundamentals of Machine Learning and Deep Learning in python using Scikit-Learn and TensorFlow.

Self-Learned Video Rain Streak Removal: When Cyclic Consistency Meets Temporal Correspondence

Pytorch implementation for the Temporal and Object Quantification Networks (TOQ-Nets).

FaceQgen: Semi-Supervised Deep Learning for Face Image Quality Assessment