Learning Discriminative Dynamics with Label Corruption for Noisy Label Detection
Label noise commonly found in real-world datasets has a detrimental impact on a model's
generalization. To effectively detect incorrectly labeled instances previous works have …
generalization. To effectively detect incorrectly labeled instances previous works have …
Machine unlearning for medical imaging
R Nasirigerdeh, N Razmi, JA Schnabel… - arXiv preprint arXiv …, 2024 - arxiv.org
Machine unlearning is the process of removing the impact of a particular set of training
samples from a pretrained model. It aims to fulfill the" right to be forgotten", which grants the …
samples from a pretrained model. It aims to fulfill the" right to be forgotten", which grants the …
LNL+ K: Learning with Noisy Labels and Noise Source Distribution Knowledge
S Wang, BA Plummer - arXiv preprint arXiv:2306.11911, 2023 - arxiv.org
Learning with noisy labels (LNL) is challenging as the model tends to memorize noisy
labels, which can lead to overfitting. Many LNL methods detect clean samples by …
labels, which can lead to overfitting. Many LNL methods detect clean samples by …
Evidential Concept Embedding Models: Towards Reliable Concept Explanations for Skin Disease Diagnosis
Due to the high stakes in medical decision-making, there is a compelling demand for
interpretable deep learning methods in medical image analysis. Concept Bottleneck Models …
interpretable deep learning methods in medical image analysis. Concept Bottleneck Models …
A Unified Framework for Connecting Noise Modeling to Boost Noise Detection
Noisy labels can impair model performance, making the study of learning with noisy labels
an important topic. Two conventional approaches are noise modeling and noise detection …
an important topic. Two conventional approaches are noise modeling and noise detection …
LNL+ K: Enhancing Learning with Noisy Labels Through Noise Source Knowledge Integration
S Wang, BA Plummer - European Conference on Computer Vision, 2024 - Springer
Learning with noisy labels (LNL) aims to train a high-performing model using a noisy
dataset. We observe that noise for a given class often comes from a limited set of categories …
dataset. We observe that noise for a given class often comes from a limited set of categories …
[PDF][PDF] Supplementary Material:“Learning Discriminative Dynamics with Label Corruption for Noisy Label Detection”
Synthetic noise: instance-dependent label noise. We detail the process of generating
instance-dependent label noise [16], which is the synthetic type label noise utilized in our …
instance-dependent label noise [16], which is the synthetic type label noise utilized in our …
Machine Learning for Drill Cuttings Analysis: Label Cleaning and Lithology Prediction
E Tolstaya, M Mezghani - 84th EAGE Annual Conference & Exhibition, 2023 - earthdoc.org
Automation of drill cuttings lithology detection is a much-desired task in reservoir
engineering, it allows quick evaluation of the formation drilled and predict possible …
engineering, it allows quick evaluation of the formation drilled and predict possible …