no code implementations • 29 Sep 2021 • Abel Brown, Benedikt Schifferer, Robert DiPietro
Successful training of deep neural networks with noisy labels is an essential capability as most real-world datasets contain some amount of mislabeled data.
Ranked #1 on Image Classification on mini WebVision 1.0 (ImageNet Top-5 Accuracy metric)
no code implementations • 1 Jan 2021 • Abel Brown, Benedikt Schifferer, Robert DiPietro
In particular, RTE achieves 93. 64% accuracy on CIFAR-10 and 66. 43% accuracy on CIFAR-100 under 80% label corruption, and achieves 76. 72% accuracy on ImageNet under 40% corruption.
no code implementations • 25 Sep 2019 • Abel Brown, Robert DiPietro
Deep neural networks have had unprecedented success in computer vision, natural language processing, and speech largely due to the ability to search for suitable task algorithms via differentiable programming.
no code implementations • 20 Jul 2019 • Robert DiPietro, Gregory D. Hager
Prior work has demonstrated the feasibility of automated activity recognition in robot-assisted surgery from motion data.
no code implementations • 8 Jun 2018 • Robert DiPietro, Gregory D. Hager
We show that it is possible to learn meaningful representations of surgical motion, without supervision, by learning to predict the future.
no code implementations • ICCV 2017 • Huseyin Coskun, Felix Achilles, Robert DiPietro, Nassir Navab, Federico Tombari
One-shot pose estimation for tasks such as body joint localization, camera pose estimation, and object tracking are generally noisy, and temporal filters have been extensively used for regularization.
no code implementations • 6 Aug 2017 • Huseyin Coskun, Felix Achilles, Robert DiPietro, Nassir Navab, Federico Tombari
One-shot pose estimation for tasks such as body joint localization, camera pose estimation, and object tracking are generally noisy, and temporal filters have been extensively used for regularization.
no code implementations • ICLR 2018 • Robert DiPietro, Christian Rupprecht, Nassir Navab, Gregory D. Hager
Recurrent neural networks (RNNs) have achieved state-of-the-art performance on many diverse tasks, from machine translation to surgical activity recognition, yet training RNNs to capture long-term dependencies remains difficult.
no code implementations • ICCV 2017 • Christian Rupprecht, Iro Laina, Robert DiPietro, Maximilian Baust, Federico Tombari, Nassir Navab, Gregory D. Hager
In future prediction, for example, many distinct outcomes are equally valid.
3 code implementations • 20 Jun 2016 • Robert DiPietro, Colin Lea, Anand Malpani, Narges Ahmidi, S. Swaroop Vedula, Gyusung I. Lee, Mija R. Lee, Gregory D. Hager
In contrast, we work on recognizing both gestures and longer, higher-level activites, or maneuvers, and we model the mapping from kinematics to gestures/maneuvers with recurrent neural networks.
Ranked #1 on Surgical Skills Evaluation on MISTIC-SIL