Training Techniques | 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 | resnet50_ssl |
SHOW MORE |
ResNet SSL is a model that uses semi-supervised learning to learn image representations. It utilises a pipeline, based on a teacher/student paradigm, that leverages a large collection of unlabelled images (up to 1 billion). Even in the case of self-training – when teacher and student models are the same - the sheer scale of unlabeled data enables significant gains. Performance is sensitive to several factors like strength of initial (teacher) model for ranking, scale and nature of unlabeled data, relationship between teacher and final model, etc.
Get started with VISSL by trying one of the Colab tutorial notebooks.
@article{DBLP:journals/corr/abs-1905-00546,
author = {I. Zeki Yalniz and
Herv{\'{e}} J{\'{e}}gou and
Kan Chen and
Manohar Paluri and
Dhruv Mahajan},
title = {Billion-scale semi-supervised learning for image classification},
journal = {CoRR},
volume = {abs/1905.00546},
year = {2019},
url = {http://arxiv.org/abs/1905.00546},
archivePrefix = {arXiv},
eprint = {1905.00546},
timestamp = {Mon, 28 Sep 2020 08:19:37 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-00546.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}
}
BENCHMARK | MODEL | METRIC NAME | METRIC VALUE | GLOBAL RANK |
---|---|---|---|---|
ImageNet | ResNet-50 Semi-supervised | Top 1 Accuracy | 79.2% | # 131 |