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

[CVPR 2021] Anycost GANs for Interactive Image Synthesis and Editing

PyTorch implementation of Hierarchical Multi-label Text Classification: An Attention-based Recurrent Network

Implementation of the paper NAST: Non-Autoregressive Spatial-Temporal Transformer for Time Series Forecasting.

PyTorch implementation of Towards Accurate Alignment in Real-time 3D Hand-Mesh Reconstruction (ICCV 2021).

Face detection using deep learning.

KE-Dialogue: Injecting knowledge graph into a fully end-to-end dialogue system.

General Assembly Capstone: NBA Game Predictor

DeepVoxels is an object-specific, persistent 3D feature embedding.

Fast algorithms to compute an approximation of the minimal volume oriented bounding box of a point cloud in 3D.

Source Code for DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances (https://arxiv.org/pdf/2012.01775.pdf)

SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data

Cryptocurrency Prediction with Artificial Intelligence (Deep Learning via LSTM Neural Networks)

Code for the paper BERT might be Overkill: A Tiny but Effective Biomedical Entity Linker based on Residual Convolutional Neural Networks

Computer Vision is an elective course of MSAI, SCSE, NTU, Singapore

A DeepStack custom model for detecting common objects in dark/night images and videos.

Implementation of StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation in PyTorch

Automatic packaging of the open-composite libs for OvGME

robomimic: A Modular Framework for Robot Learning from Demonstration

A colab notebook for training Stylegan2-ada on colab, transfer learning onto your own dataset.

[Pedestron] Generalizable Pedestrian Detection: The Elephant In The Room. @ CVPR2021