Do imagenet classifiers generalize to imagenet? B Recht, R Roelofs, L Schmidt, V Shankar International conference on machine learning, 5389-5400, 2019 | 1544 | 2019 |
The marginal value of adaptive gradient methods in machine learning AC Wilson, R Roelofs, M Stern, N Srebro, B Recht Advances in neural information processing systems 30, 2017 | 1232 | 2017 |
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time M Wortsman, G Ilharco, SY Gadre, R Roelofs, R Gontijo-Lopes, ... International conference on machine learning, 23965-23998, 2022 | 527 | 2022 |
Robust fine-tuning of zero-shot models M Wortsman, G Ilharco, JW Kim, M Li, S Kornblith, R Roelofs, RG Lopes, ... Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2022 | 428 | 2022 |
Do cifar-10 classifiers generalize to cifar-10? B Recht, R Roelofs, L Schmidt, V Shankar arXiv preprint arXiv:1806.00451, 2018 | 415 | 2018 |
A meta-analysis of overfitting in machine learning R Roelofs, V Shankar, B Recht, S Fridovich-Keil, M Hardt, J Miller, ... Advances in Neural Information Processing Systems 32, 2019 | 189 | 2019 |
Scene transformer: A unified architecture for predicting multiple agent trajectories J Ngiam, B Caine, V Vasudevan, Z Zhang, HTL Chiang, J Ling, R Roelofs, ... arXiv preprint arXiv:2106.08417, 2021 | 188 | 2021 |
Evaluating machine accuracy on imagenet V Shankar, R Roelofs, H Mania, A Fang, B Recht, L Schmidt International Conference on Machine Learning, 8634-8644, 2020 | 150 | 2020 |
Adamatch: A unified approach to semi-supervised learning and domain adaptation D Berthelot, R Roelofs, K Sohn, N Carlini, A Kurakin arXiv preprint arXiv:2106.04732, 2021 | 127 | 2021 |
Do image classifiers generalize across time? V Shankar, A Dave, R Roelofs, D Ramanan, B Recht, L Schmidt Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021 | 75 | 2021 |
Mitigating bias in calibration error estimation R Roelofs, N Cain, J Shlens, MC Mozer International Conference on Artificial Intelligence and Statistics, 4036-4054, 2022 | 69 | 2022 |
Soft calibration objectives for neural networks A Karandikar, N Cain, D Tran, B Lakshminarayanan, J Shlens, MC Mozer, ... Advances in Neural Information Processing Systems 34, 29768-29779, 2021 | 69 | 2021 |
Scene transformer: A unified multi-task model for behavior prediction and planning J Ngiam, B Caine, V Vasudevan, Z Zhang, HTL Chiang, J Ling, R Roelofs, ... arXiv preprint arXiv:2106.08417 2 (7), 2021 | 66 | 2021 |
The evolution of out-of-distribution robustness throughout fine-tuning A Andreassen, Y Bahri, B Neyshabur, R Roelofs arXiv preprint arXiv:2106.15831, 2021 | 59 | 2021 |
Large scale kernel learning using block coordinate descent S Tu, R Roelofs, S Venkataraman, B Recht arXiv preprint arXiv:1602.05310, 2016 | 43 | 2016 |
Imitation is not enough: Robustifying imitation with reinforcement learning for challenging driving scenarios Y Lu, J Fu, G Tucker, X Pan, E Bronstein, R Roelofs, B Sapp, B White, ... 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2023 | 41 | 2023 |
When does dough become a bagel? analyzing the remaining mistakes on imagenet V Vasudevan, B Caine, R Gontijo Lopes, S Fridovich-Keil, R Roelofs Advances in Neural Information Processing Systems 35, 6720-6734, 2022 | 41 | 2022 |
Pseudo-labeling for scalable 3d object detection B Caine, R Roelofs, V Vasudevan, J Ngiam, Y Chai, Z Chen, J Shlens arXiv preprint arXiv:2103.02093, 2021 | 41 | 2021 |
Do cifar-10 classifiers generalize to cifar-10? 2018 B Recht, R Roelofs, L Schmidt, V Shankar URL https://arxiv. org/abs, 1806 | 32 | 1806 |
Measuring Generalization and overfitting in Machine learning R Roelofs University of California, Berkeley, 2019 | 31 | 2019 |