198 citations · 206 across the 12 of their papers we have counts for
15 papers · 1 filter
An accurate detection is not all you need to combat label noise in web-noisy datasets
Paul Albert, Jack Valmadre, Eric Arazo +3
Training a classifier on web-crawled data demands learning algorithms that are robust to annotation errors and irrelevant examples. This paper builds upon the recent empirical obse…
Energy-Efficient Uncertainty-Aware Biomass Composition Prediction at the Edge
Muhammad Zawish, Paul Albert, Flavio Esposito +2
Clover fixates nitrogen from the atmosphere to the ground, making grass-clover mixtures highly desirable to reduce external nitrogen fertilization. Herbage containing clover additi…
Is your noise correction noisy? PLS: Robustness to label noise with two stage detection
Paul Albert, Eric Arazo, Tarun Krishna +2
Designing robust algorithms capable of training accurate neural networks on uncurated datasets from the web has been the subject of much research as it reduces the need for time co…
Embedding contrastive unsupervised features to cluster in- and out-of-distribution noise in corrupted image datasets
Paul Albert, Eric Arazo, Noel E. O'Connor +1
Using search engines for web image retrieval is a tempting alternative to manual curation when creating an image dataset, but their main drawback remains the proportion of incorrec…
Utilizing unsupervised learning to improve sward content prediction and herbage mass estimation
Paul Albert, Mohamed Saadeldin, Badri Narayanan +5
Sward species composition estimation is a tedious one. Herbage must be collected in the field, manually separated into components, dried and weighed to estimate species composition…
Unsupervised domain adaptation and super resolution on drone images for autonomous dry herbage biomass estimation
Paul Albert, Mohamed Saadeldin, Badri Narayanan +5
Herbage mass yield and composition estimation is an important tool for dairy farmers to ensure an adequate supply of high quality herbage for grazing and subsequently milk producti…
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…
Semi-supervised dry herbage mass estimation using automatic data and synthetic images
Paul Albert, Mohamed Saadeldin, Badri Narayanan +5
Monitoring species-specific dry herbage biomass is an important aspect of pasture-based milk production systems. Being aware of the herbage biomass in the field enables farmers to…
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…
Extracting Pasture Phenotype and Biomass Percentages using Weakly Supervised Multi-target Deep Learning on a Small Dataset
Badri Narayanan, Mohamed Saadeldin, Paul Albert +2
The dairy industry uses clover and grass as fodder for cows. Accurate estimation of grass and clover biomass yield enables smart decisions in optimizing fertilization and seeding d…
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…
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…
Towards Robust Learning with Different Label Noise Distributions
Diego Ortego, Eric Arazo, Paul Albert +2
Noisy labels are an unavoidable consequence of labeling processes and detecting them is an important step towards preventing performance degradations in Convolutional Neural Networ…
Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning
Eric Arazo, Diego Ortego, Paul Albert +2
Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active research topic due to its key role on relaxing human supervision. In the context of…
Unsupervised Label Noise Modeling and Loss Correction
Eric Arazo, Diego Ortego, Paul Albert +2
Despite being robust to small amounts of label noise, convolutional neural networks trained with stochastic gradient methods have been shown to easily fit random labels. When there…