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

Exponential Graph is Provably Efficient for Decentralized Deep Training

WeakVRD-Captioning - Implementation of paper Improving Image Captioning with Better Use of Caption

[CVPR 2021] Monocular depth estimation using wavelets for efficiency

Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

FID calculation with proper image resizing and quantization steps

Identify the emotion of multiple speakers in an Audio Segment

implement of SwiftNet:Real-time Video Object Segmentation

(Python, R, C/C++) Isolation Forest and variations such as SCiForest and EIF, with some additions (outlier detection + similarity + NA imputation)

face2comics by Sxela (Alex Spirin) - face2comics datasets

From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement (CVPR'2020)

This is the official implementation of 3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection, built on SECOND.

A toolset of Python programs for signal modeling and indentification via sparse semilinear autoregressors.

Notspot robot simulation - Python version

Graph Transformer Architecture. Source code for

A simple Python library for stochastic graphical ecological models

Your interactive network visualizing dashboard

PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillation

Codebase for Attentive Neural Hawkes Process (A-NHP) and Attentive Neural Datalog Through Time (A-NDTT)

Training DiffWave using variational method from Variational Diffusion Models.