Awesome

Self-Supervised Pyramid Representation Learning <br>for Multi-Label Visual Analysis and Beyond

This repository provides the official Pytorch implementation of pretraining and downstream evaluations for SS-PRL.

:paperclip: Paper Link :pencil2: Citations

Learning of Patch-Based Pyramid Representation
Cross-Scale Patch-Level Correlation Learning with Correlation Learners

<h2> Table of Contents</h2> <ul> <li> <a href="#books-prepare-dataset">Prepare Dataset</a> <ul>  </ul> </li> <li> <a href="#running-usage---training">Usage</a> </li> <li> <a href="#bicyclist-downstream-tasks">Downstream tasks</a> </li> <li> <a href="#citations">Citations</a> </li> </ul>

:books: Prepare Dataset

Please refer to Pretrained_Dataset and Downstream Tasks for further details.

Tasks	Datasets:point_down:
Pre-Training	ImageNet <br> COCO
Downstream	Pascal VOC <br> COCO

:running: Usage - Training

Requirements

Python 3.6
PyTorch = 1.4.0
torchvision = 0.5.0
CUDA 10.1 (Check with nvcc --version)
Apex 0.1 (Installation)
scipy, pandas, numpy

conda install pytorch==1.4.0 torchvision==0.5.0 cudatoolkit=10.1 -c pytorch

git clone "https://github.com/NVIDIA/apex"
cd apex
git checkout 4a1aa97e31ca87514e17c3cd3bbc03f4204579d0
python setup.py install --cuda_ext

Training with the shell script.

For further details, take a look at the source file | dataset definition | utilities

# Training Checklist:
# 1. modify the DATASET_PATH and EXPERIMENT_PATH in the script
# 2. BATCH_PER_GPU denotes the batch size per gpu, while --nproc_per_node denotes the number of gpus
# 3. modify the parameters
cd SS-PRL
bash train_SSPRL.sh

:bicyclist: Downstream tasks

Download the pretrained models

We provide the checkpoint files of SS-PRL and other SoTA used in our experiments, including
- SwAV
- MoCo
- DenseCL
- BYOL
- InsLoc
- MaskCo
```
# Download the checkpoints with this command
bash get_premodels.sh
```
Transferring to Multi-Label Visual Analysis tasks:

Please Refer to Readme files for Classification, Object-Detection, and Semantic Segmentation tasks.

Citations

@misc{hsieh2022selfsupervised,
    title={Self-Supervised Pyramid Representation Learning for Multi-Label Visual Analysis and Beyond},
    author={Cheng-Yen Hsieh and Chih-Jung Chang and Fu-En Yang and Yu-Chiang Frank Wang},
    year={2022},
    eprint={2208.14439},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

Acknowledgement

Thanks the Facebook-Research-SwAV for its open-source project.