Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Kappiyath, Adarsh"'
Neural networks trained on biased datasets tend to inadvertently learn spurious correlations, hindering generalization. We formally prove that (1) samples that exhibit spurious correlations lie on a lower rank manifold relative to the ones that do no
Externí odkaz:
http://arxiv.org/abs/2403.19863
Several methods for discovering interpretable directions in the latent space of pre-trained GANs have been proposed. Latent semantics discovered by unsupervised methods are relatively less disentangled than supervised methods since they do not use pr
Externí odkaz:
http://arxiv.org/abs/2112.08835
Publikováno v:
2021 International Joint Conference on Neural Networks (IJCNN), 2021, pp. 1-8
We propose Disentanglement based Active Learning (DAL), a new active learning technique based on self-supervision which leverages the concept of disentanglement. Instead of requesting labels from human oracle, our method automatically labels the majo
Externí odkaz:
http://arxiv.org/abs/1912.07018
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:7078-7086
Several methods for discovering interpretable directions in the latent space of pre-trained GANs have been proposed. Latent semantics discovered by unsupervised methods are relatively less disentangled than supervised methods since they do not use pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0a2a8c6051ae7c55639e6f2c8317077f
https://doi.org/10.1609/aaai.v36i7.20667
https://doi.org/10.1609/aaai.v36i7.20667
