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

Tightness-aware Evaluation Protocol for Scene Text Detection

Machine learning framework for both deep learning and traditional algorithms

A Python parser that takes the content of a text file and then reads it into variables.

[CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting

MIMO-UNet - Official Pytorch Implementation

Adjusting for Autocorrelated Errors in Neural Networks for Time Series

PyTorchMemTracer - Depict GPU memory footprint during DNN training of PyTorch

FairEdit: Preserving Fairness in Graph Neural Networks through Greedy Graph Editing

A Free and Open Source Python Library for Multiobjective Optimization

Code for Ditto: Building Digital Twins of Articulated Objects from Interaction

Implementation of Bagging and AdaBoost Algorithm

Image super-resolution through deep learning

BEAMetrics: Benchmark to Evaluate Automatic Metrics in Natural Language Generation

Deep Reinforcement Learning by using an on-policy adaptation of Maximum a Posteriori Policy Optimization (MPO)

Codes for Causal Semantic Generative model (CSG), the model proposed in "Learning Causal Semantic Representation for Out-of-Distribution Prediction" (NeurIPS-21)

The offcial repository for 'CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos', SIGIR2022

Implementation of Memory-Efficient Neural Networks with Multi-Level Generation, ICCV 2021

Find-Lane-Line - Use openCV library and Python to detect the road-lane-line

CLDF dataset derived from Robbeets et al.'s "Triangulation Supports Agricultural Spread" from 2021

Code release for DS-NeRF (Depth-supervised Neural Radiance Fields)