ID	alexnet_in1k_oss_rotnet
lr	0.1
Classes	1000
Momentum	0.9
Weight Decay	0.0005

ID	rn50_in1k_rotnet
Epochs	105
Layers	50
Classes	1000
Weight Decay	0.0001
Width Multiplier	1

ID	rn50_in22k_rotnet
Epochs	105
Layers	50
Classes	1000
Weight Decay	0.0001
Width Multiplier	1

RotNet

facebookresearch / vissl

Last updated on Feb 27, 2021

Parameters 61 Million

FLOPs 715 Million

File Size 217.63 MB

Training Data ImageNet

Training Resources 1 NVIDIA Titan X GPU

Training Time 2 days

Training Techniques	RotNet, Weight Decay, SGD with Momentum
Architecture	Convolution, Dropout, Dense Connections, ReLU, Max Pooling, Softmax
ID	alexnet_in1k_oss_rotnet
lr	0.1
Classes	1000
Momentum	0.9
Weight Decay	0.0005
SHOW MORE
SHOW LESS

Parameters 26 Million

FLOPs 4 Billion

File Size 179.83 MB

Training Data ImageNet

Training Resources 8 NVIDIA V100 GPUs

Training Time

Training Techniques	RotNet, Weight Decay, SGD with Momentum
Architecture	1x1 Convolution, Bottleneck Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Block, Residual Connection, ReLU, Max Pooling, Softmax
ID	rn50_in1k_rotnet
Epochs	105
Layers	50
Classes	1000
Weight Decay	0.0001
Width Multiplier	1
SHOW MORE
SHOW LESS

Parameters 26 Million

FLOPs 4 Billion

File Size 180.02 MB

Training Data ImageNet

Training Resources 8 NVIDIA V100 GPUs

Training Time

Training Techniques	RotNet, Weight Decay, SGD with Momentum
Architecture	1x1 Convolution, Bottleneck Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Block, Residual Connection, ReLU, Max Pooling, Softmax
ID	rn50_in22k_rotnet
Epochs	105
Layers	50
Classes	1000
Weight Decay	0.0001
Width Multiplier	1
SHOW MORE
SHOW LESS

README.md

Summary

RotNet is a self-supervision approach that relies on predicting image rotations as the pretext task in order to learn image representations.

How do I train this model?

Get started with VISSL by trying one of the Colab tutorial notebooks.

Citation

@article{DBLP:journals/corr/abs-1803-07728,
  author    = {Spyros Gidaris and
               Praveer Singh and
               Nikos Komodakis},
  title     = {Unsupervised Representation Learning by Predicting Image Rotations},
  journal   = {CoRR},
  volume    = {abs/1803.07728},
  year      = {2018},
  url       = {http://arxiv.org/abs/1803.07728},
  archivePrefix = {arXiv},
  eprint    = {1803.07728},
  timestamp = {Mon, 13 Aug 2018 16:46:04 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1803-07728.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@misc{goyal2021vissl,
  author =       {Priya Goyal and Benjamin Lefaudeux and Mannat Singh and Jeremy Reizenstein and Vinicius Reis and 
                  Min Xu and and Matthew Leavitt and Mathilde Caron and Piotr Bojanowski and Armand Joulin and 
                  Ishan Misra},
  title =        {VISSL},
  howpublished = {\url{https://github.com/facebookresearch/vissl}},
  year =         {2021}
}

Results

Image Classification on ImageNet

Image Classification

BENCHMARK	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
ImageNet	RotNet ResNet-50 (Goyal19, ImageNet-22K)	Top 1 Accuracy	54.89%	# 308
ImageNet	RotNet ResNet-50 (Goyal19, ImageNet-1K)	Top 1 Accuracy	48.2%	# 315
ImageNet	RotNet AlexNet (ImageNet-1K)	Top 1 Accuracy	39.51%	# 322