Search Results for author:
Found 10 papers, 1 papers with code
Robust Temporal Ensembling for Learning with Noisy Labels
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)
Robust Temporal Ensembling
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.
Neural Video Encoding
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.
Automated Surgical Activity Recognition with One Labeled Sequence
Prior work has demonstrated the feasibility of automated activity recognition in robot-assisted surgery from motion data.
Unsupervised Learning for Surgical Motion by Learning to Predict the Future
We show that it is possible to learn meaningful representations of surgical motion, without supervision, by learning to predict the future.
Long Short-Term Memory Kalman Filters: Recurrent Neural Estimators for Pose Regularization
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.
Long Short-Term Memory Kalman Filters:Recurrent Neural Estimators for Pose Regularization
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.
Analyzing and Exploiting NARX Recurrent Neural Networks for Long-Term Dependencies
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.
Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses
In future prediction, for example, many distinct outcomes are equally valid.
Recognizing Surgical Activities with Recurrent Neural Networks
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
