| An image is worth 16x16 words: Transformers for image recognition at scale A Dosovitskiy, L Beyer, A Kolesnikov, D Weissenborn, X Zhai, ... arXiv preprint arXiv:2010.11929, 2020 | 6122 | 2020 |
| Parameter-efficient transfer learning for NLP N Houlsby, A Giurgiu, S Jastrzebski, B Morrone, Q De Laroussilhe, ... International Conference on Machine Learning, 2790-2799, 2019 | 590 | 2019 |
| Big transfer (bit): General visual representation learning A Kolesnikov, L Beyer, X Zhai, J Puigcerver, J Yung, S Gelly, N Houlsby European conference on computer vision, 491-507, 2020 | 540 | 2020 |
| Mlp-mixer: An all-mlp architecture for vision IO Tolstikhin, N Houlsby, A Kolesnikov, L Beyer, X Zhai, T Unterthiner, ... Advances in Neural Information Processing Systems 34, 24261-24272, 2021 | 469 | 2021 |
| Bayesian active learning for classification and preference learning N Houlsby, F Huszár, Z Ghahramani, M Lengyel arXiv preprint arXiv:1112.5745, 2011 | 438 | 2011 |
| An image is worth 16x16 words: Transformers for image recognition at scale. arXiv 2020 A Dosovitskiy, L Beyer, A Kolesnikov, D Weissenborn, X Zhai, ... arXiv preprint arXiv:2010.11929, 2010 | 346 | 2010 |
| Underspecification presents challenges for credibility in modern machine learning A D'Amour, K Heller, D Moldovan, B Adlam, B Alipanahi, A Beutel, ... arXiv preprint arXiv:2011.03395, 2020 | 297 | 2020 |
| Scaling vision transformers X Zhai, A Kolesnikov, N Houlsby, L Beyer Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022 | 279* | 2022 |
| Self-supervised gans via auxiliary rotation loss T Chen, X Zhai, M Ritter, M Lucic, N Houlsby Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2019 | 216 | 2019 |
| Adaptive Bayesian quantum tomography F Huszár, NMT Houlsby Physical Review A 85 (5), 052120, 2012 | 151 | 2012 |
| Ask the right questions: Active question reformulation with reinforcement learning C Buck, J Bulian, M Ciaramita, W Gajewski, A Gesmundo, N Houlsby, ... arXiv preprint arXiv:1705.07830, 2017 | 140 | 2017 |
| Probabilistic matrix factorization with non-random missing data JM Hernández-Lobato, N Houlsby, Z Ghahramani International Conference on Machine Learning, 1512-1520, 2014 | 137 | 2014 |
| Collaborative gaussian processes for preference learning N Houlsby, F Huszar, Z Ghahramani, J Hernández-lobato Advances in neural information processing systems 25, 2012 | 130 | 2012 |
| Transfer learning with neural automl C Wong, N Houlsby, Y Lu, A Gesmundo Advances in neural information processing systems 31, 2018 | 97 | 2018 |
| A large-scale study of representation learning with the visual task adaptation benchmark X Zhai, J Puigcerver, A Kolesnikov, P Ruyssen, C Riquelme, M Lucic, ... arXiv preprint arXiv:1910.04867, 2019 | 92 | 2019 |
| Experimental adaptive Bayesian tomography KS Kravtsov, SS Straupe, IV Radchenko, NMT Houlsby, F Huszár, ... Physical Review A 87 (6), 062122, 2013 | 89 | 2013 |
| On self modulation for generative adversarial networks T Chen, M Lucic, N Houlsby, S Gelly arXiv preprint arXiv:1810.01365, 2018 | 81 | 2018 |
| Large scale learning of general visual representations for transfer A Kolesnikov, L Beyer, X Zhai, J Puigcerver, J Yung, S Gelly, N Houlsby arXiv preprint arXiv:1912.11370 2 (8), 2019 | 77 | 2019 |
| Scaling vision with sparse mixture of experts C Riquelme, J Puigcerver, B Mustafa, M Neumann, R Jenatton, ... Advances in Neural Information Processing Systems 34, 8583-8595, 2021 | 67 | 2021 |
| Cold-start active learning with robust ordinal matrix factorization N Houlsby, JM Hernández-Lobato, Z Ghahramani International conference on machine learning, 766-774, 2014 | 65 | 2014 |
Zoubin GhahramaniProfessor, University of Cambridge, and Distinguished Researcher, GoogleVerified email at eng.cam.ac.uk
