Home

Awesome

FAIR Self-Supervision Benchmark is deprecated. Please see VISSL, a ground-up rewrite of benchmark in PyTorch.

FAIR Self-Supervision Benchmark

This code provides various benchmark (and legacy) tasks for evaluating quality of visual representations learned by various self-supervision approaches. This code corresponds to our work on Scaling and Benchmarking Self-Supervised Visual Representation Learning. The code is written in Python and can be used to evaluate both PyTorch and Caffe2 models (see this). We hope that this benchmark release will provided a consistent evaluation strategy that will allow measuring the progress in self-supervision easily.

Introduction

The goal of fair_self_supervision_benchmark is to standardize the methodology for evaluating quality of visual representations learned by various self-supervision approaches. Further, it provides evaluation on a variety of tasks as follows:

Benchmark tasks: The benchmark tasks are based on principle: a good representation (1) transfers to many different tasks, and, (2) transfers with limited supervision and limited fine-tuning. The tasks are as follows.

<p align="center"> <img src="demo/img-cls.png" alt="Image Classification" title="Image Classification" width="200" /> <img src="demo/obj-detection.png" alt="Object Detection" title="Object Detection" width="200" /> <img src="demo/surface-normal.png" alt="Surface Normal Estimation" title="Surface Normal Estimation" width="200" /> <img src="demo/visual-navigation.png" alt="Visual Navigation" title="Visual Navigation" width="200" /> </p>

These Benchmark tasks use the network architectures:

Legacy tasks: We also classify some commonly used evaluation tasks as legacy tasks for reasons mentioned in Section 7 of paper. The tasks are as follows:

License

fair_self_supervision_benchmark is CC-NC 4.0 International licensed, as found in the LICENSE file.

Citation

If you use fair_self_supervision_benchmark in your research or wish to refer to the baseline results published in the paper, please use the following BibTeX entry.

@article{goyal2019scaling,
  title={Scaling and Benchmarking Self-Supervised Visual Representation Learning},
  author={Goyal, Priya and Mahajan, Dhruv and Gupta, Abhinav and Misra, Ishan},
  journal={arXiv preprint arXiv:1905.01235},
  year={2019}
}

Installation

Please find installation instructions in INSTALL.md.

Getting Started

After installation, please see GETTING_STARTED.md for how to run various benchmark tasks.

Model Zoo

We provide models used in our paper in the MODEL_ZOO.

References