| Training Techniques | DeepCluster, Weight Decay, SGD with Momentum |
|---|---|
| Architecture | Dropout, Batch Normalization, Convolution, Dropout, Dense Connections, ReLU, Max Pooling, Softmax |
| ID | alexnet_in1k_oss_deepcluster |
| SHOW MORE |
DeepCluster is a self-supervision approach for learning image representations. DeepCluster iteratively groups the features with a standard clustering algorithm, k-means, and uses the subsequent assignments as supervision to update the weights of the network
Get started with VISSL by trying one of the Colab tutorial notebooks.
@article{DBLP:journals/corr/abs-1807-05520,
author = {Mathilde Caron and
Piotr Bojanowski and
Armand Joulin and
Matthijs Douze},
title = {Deep Clustering for Unsupervised Learning of Visual Features},
journal = {CoRR},
volume = {abs/1807.05520},
year = {2018},
url = {http://arxiv.org/abs/1807.05520},
archivePrefix = {arXiv},
eprint = {1807.05520},
timestamp = {Mon, 13 Aug 2018 16:46:44 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1807-05520.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}
}
Image Classification
| BENCHMARK | MODEL | METRIC NAME | METRIC VALUE | GLOBAL RANK |
|---|---|---|---|---|
| ImageNet | DeepCluster AlexNet (ImageNet-1K) | Top 1 Accuracy | 37.88% | # 323 |
