most citedUsing Early-Learning Regularization to Classify Real-World Noisy Data

1 citations · 2 across the 2 of their papers we have counts for

collaborators

2 papers

cs.LG2024★ 1 cited

Indirectly Parameterized Concrete Autoencoders

Alfred Nilsson, Klas Wijk, Sai bharath chandra Gutha +7

Feature selection is a crucial task in settings where data is high-dimensional or acquiring the full set of features is costly. Recent developments in neural network-based embedded…

cs.CV2021★ 1 cited

Using Early-Learning Regularization to Classify Real-World Noisy Data

Alessio Galatolo, Alfred Nilsson, Roderick Karlemstrand +1

The memorization problem is well-known in the field of computer vision. Liu et al. propose a technique called Early-Learning Regularization, which improves accuracy on the CIFAR da…