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.