Training scale-invariant neural networks on the sphere can happen in three regimes M Kodryan, E Lobacheva, M Nakhodnov, DP Vetrov Advances in Neural Information Processing Systems 35, 14058-14070, 2022 | 8 | 2022 |
Styledomain: Efficient and lightweight parameterizations of stylegan for one-shot and few-shot domain adaptation A Alanov, V Titov, M Nakhodnov, D Vetrov Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023 | 2 | 2023 |
Loss function dynamics and landscape for deep neural networks trained with quadratic loss MS Nakhodnov, MS Kodryan, EM Lobacheva, DS Vetrov Doklady Mathematics 106 (Suppl 1), S43-S62, 2022 | 1 | 2022 |
StyleDomain: Analysis of StyleSpace for Domain Adaptation of StyleGAN. A Alanov, V Titov, M Nakhodnov, D Vetrov arXiv preprint arXiv 2212, 2022 | 1 | 2022 |