A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2024; you can also visit the original URL.
The file type is application/pdf.
Filters
FroSSL: Frobenius Norm Minimization for Efficient Multiview Self-Supervised Learning
[article]
2024
arXiv
pre-print
Preserved Fulltext
Other Versions
Self-supervised learning (SSL) is a popular paradigm for representation learning. ...
We also show that FroSSL learns competitive representations on linear probe evaluation when used to train a ResNet18 on several datasets, including STL-10, Tiny Imagenet, and Imagenet-100. ...
Acknowledgements This research is based upon work supported in part by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via 2021-2011000005 ...
arXiv:2310.02903v3
fatcat:rhhdksxxnjailm76hq4uif4v54
Matrix Information Theory for Self-Supervised Learning
[article]
2024
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2024; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2024 pre-print arXiv:2305.17326v5 fatcat:rirsnadh5ffchb3lovjwsxokraOther Versions
Specifically, when performing transfer learning tasks on MS-COCO, our method outperforms previous SOTA methods such as MoCo v2 and BYOL up to 3.3% with only 400 epochs compared to 800 epochs pre-training ...
Experimental results reveal that Matrix-SSL outperforms state-of-the-art methods on the ImageNet dataset under linear evaluation settings and on MS-COCO for transfer learning tasks. ...
We perform t-SNE [73] visualization on the last checkpoint of each method with the help of scikit-learn [54] . ...
arXiv:2305.17326v6
fatcat:motzai6ydzfrxmg5xeczpfgzwm
Unconstrained Stochastic CCA: Unifying Multiview and Self-Supervised Learning
[article]
2024
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2023 pre-print arXiv:2310.01012v2 fatcat:hr6vgf7xd5anfpx3fen7swtovyOther Versions
Finally, we apply our algorithms to match the performance of 'CCA-family' Self-Supervised Learning (SSL) methods on CIFAR-10 and CIFAR-100 with minimal hyper-parameter tuning, and also present theory to ...
The Canonical Correlation Analysis (CCA) family of methods is foundational in multiview learning. ...
EMP-SSL: rowards self-supervised learning in one training epoch. arXiv preprint arXiv:2304.03977, 2023. ...
arXiv:2310.01012v4
fatcat:ioycsalmtvhtrcletvcsla342i