Search Results for author:
Found 16 papers, 10 papers with code
Energy-Efficient Uncertainty-Aware Biomass Composition Prediction at the Edge
We report that although pruned networks are accurate on controlled, high-quality images of the grass, they struggle to generalize to real-world smartphone images that are blurry or taken from challenging angles.
Unifying Synergies between Self-supervised Learning and Dynamic Computation
Computationally expensive training strategies make self-supervised learning (SSL) impractical for resource constrained industrial settings.
Is your noise correction noisy? PLS: Robustness to label noise with two stage detection
Experiments demonstrate the state-of-the-art performance of our Pseudo-Loss Selection (PLS) algorithm on a variety of benchmark datasets including curated data synthetically corrupted with in-distribution and out-of-distribution noise, and two real world web noise datasets.
Embedding contrastive unsupervised features to cluster in- and out-of-distribution noise in corrupted image datasets
These noisy samples have been evidenced by previous works to be a mixture of in-distribution (ID) samples, assigned to the incorrect category but presenting similar visual semantics to other classes in the dataset, and out-of-distribution (OOD) images, which share no semantic correlation with any category from the dataset.
Utilizing unsupervised learning to improve sward content prediction and herbage mass estimation
Sward species composition estimation is a tedious one.
Unsupervised domain adaptation and super resolution on drone images for autonomous dry herbage biomass estimation
In this context, deep learning algorithms offer a tempting alternative to the usual means of sward composition estimation, which involves the destructive process of cutting a sample from the herbage field and sorting by hand all plant species in the herbage.
How Important is Importance Sampling for Deep Budgeted Training?
We suggest that, given a specific budget, the best course of action is to disregard the importance and introduce adequate data augmentation; e. g. when reducing the budget to a 30% in CIFAR-10/100, RICAP data augmentation maintains accuracy, while importance sampling does not.
Semi-supervised dry herbage mass estimation using automatic data and synthetic images
Deep learning for computer vision is a powerful tool in this context as it can accurately estimate the dry biomass of a herbage parcel using images of the grass canopy taken using a portable device.
Addressing out-of-distribution label noise in webly-labelled data
We propose a simple solution to bridge the gap with a fully clean dataset using Dynamic Softening of Out-of-distribution Samples (DSOS), which we design on corrupted versions of the CIFAR-100 dataset, and compare against state-of-the-art algorithms on the web noise perturbated MiniImageNet and Stanford datasets and on real label noise datasets: WebVision 1. 0 and Clothing1M.
Extracting Pasture Phenotype and Biomass Percentages using Weakly Supervised Multi-target Deep Learning on a Small Dataset
In this paper, we demonstrate that applying data augmentation and transfer learning is effective in predicting multi-target biomass percentages of different plant species, even with a small training dataset.
The Importance of Importance Sampling for Deep Budgeted Training
For example, training in CIFAR-10/100 with 30% of the full training budget, a uniform sampling strategy with certain data augmentation surpasses the performance of 100% budget models trained with standard data augmentation.
Multi-Objective Interpolation Training for Robustness to Label Noise
We further propose a novel label noise detection method that exploits the robust feature representations learned via contrastive learning to estimate per-sample soft-labels whose disagreements with the original labels accurately identify noisy samples.
Ranked #21 on
Image Classification
on mini WebVision 1.0
Reliable Label Bootstrapping for Semi-Supervised Learning
We propose Reliable Label Bootstrapping (ReLaB), an unsupervised preprossessing algorithm which improves the performance of semi-supervised algorithms in extremely low supervision settings.
Towards Robust Learning with Different Label Noise Distributions
However, we show that different noise distributions make the application of this trick less straightforward and propose to continuously relabel all images to reveal a discriminative loss against multiple distributions.
Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning
In the context of image classification, recent advances to learn from unlabeled samples are mainly focused on consistency regularization methods that encourage invariant predictions for different perturbations of unlabeled samples.
Unsupervised Label Noise Modeling and Loss Correction
Specifically, we propose a beta mixture to estimate this probability and correct the loss by relying on the network prediction (the so-called bootstrapping loss).
Ranked #44 on
Image Classification
on Clothing1M
