activity
20192022
most citedUnsupervised Label Noise Modeling and Loss Correction

198 citations · 200 across the 4 of their papers we have counts for

collaborators

10 papers

cs.CV20222 cited

Domain Randomization for Object Counting

Enric Moreu, Kevin McGuinness, Diego Ortego +1

Recently, the use of synthetic datasets based on game engines has been shown to improve the performance of several tasks in computer vision. However, these datasets are typically o…

cs.CV2021

How Important is Importance Sampling for Deep Budgeted Training?

Eric Arazo, Diego Ortego, Paul Albert +2

Long iterative training processes for Deep Neural Networks (DNNs) are commonly required to achieve state-of-the-art performance in many computer vision tasks. Importance sampling a…

cs.CV2021

Addressing out-of-distribution label noise in webly-labelled data

Paul Albert, Diego Ortego, Eric Arazo +2

A recurring focus of the deep learning community is towards reducing the labeling effort. Data gathering and annotation using a search engine is a simple alternative to generating…

cs.CV2020

Multi-Objective Interpolation Training for Robustness to Label Noise

Diego Ortego, Eric Arazo, Paul Albert +2

Deep neural networks trained with standard cross-entropy loss memorize noisy labels, which degrades their performance. Most research to mitigate this memorization proposes new robu…

cs.SD2020

Unsupervised Contrastive Learning of Sound Event Representations

Eduardo Fonseca, Diego Ortego, Kevin McGuinness +2

Self-supervised representation learning can mitigate the limitations in recognition tasks with few manually labeled data but abundant unlabeled data---a common scenario in sound ev…

cs.CV2020

Reliable Label Bootstrapping for Semi-Supervised Learning

Paul Albert, Diego Ortego, Eric Arazo +2

Reducing the amount of labels required to train convolutional neural networks without performance degradation is key to effectively reduce human annotation efforts. We propose Reli…