Learning from noisy labels with deep neural networks: A survey
Deep learning has achieved remarkable success in numerous domains with help from large
amounts of big data. However, the quality of data labels is a concern because of the lack of …
amounts of big data. However, the quality of data labels is a concern because of the lack of …
Breaking the dilemma of medical image-to-image translation
L Kong, C Lian, D Huang, Y Hu… - Advances in Neural …, 2021 - proceedings.neurips.cc
Abstract Supervised Pix2Pix and unsupervised Cycle-consistency are two modes that
dominate the field of medical image-to-image translation. However, neither modes are ideal …
dominate the field of medical image-to-image translation. However, neither modes are ideal …
Image classification with deep learning in the presence of noisy labels: A survey
Image classification systems recently made a giant leap with the advancement of deep
neural networks. However, these systems require an excessive amount of labeled data to be …
neural networks. However, these systems require an excessive amount of labeled data to be …
Co-learning: Learning from noisy labels with self-supervision
Noisy labels, resulting from mistakes in manual labeling or webly data collecting for
supervised learning, can cause neural networks to overfit the misleading information and …
supervised learning, can cause neural networks to overfit the misleading information and …
Beyond class-conditional assumption: A primary attempt to combat instance-dependent label noise
Supervised learning under label noise has seen numerous advances recently, while
existing theoretical findings and empirical results broadly build up on the class-conditional …
existing theoretical findings and empirical results broadly build up on the class-conditional …
Learning cross-modal retrieval with noisy labels
Recently, cross-modal retrieval is emerging with the help of deep multimodal learning.
However, even for unimodal data, collecting large-scale well-annotated data is expensive …
However, even for unimodal data, collecting large-scale well-annotated data is expensive …
Retrieve: Coreset selection for efficient and robust semi-supervised learning
Semi-supervised learning (SSL) algorithms have had great success in recent years in
limited labeled data regimes. However, the current state-of-the-art SSL algorithms are …
limited labeled data regimes. However, the current state-of-the-art SSL algorithms are …
Distributionally robust learning
R Chen, IC Paschalidis - Foundations and Trends® in …, 2020 - nowpublishers.com
This monograph develops a comprehensive statistical learning framework that is robust to
(distributional) perturbations in the data using Distributionally Robust Optimization (DRO) …
(distributional) perturbations in the data using Distributionally Robust Optimization (DRO) …
Robustness to adversarial perturbations in learning from incomplete data
What is the role of unlabeled data in an inference problem, when the presumed underlying
distribution is adversarially perturbed? To provide a concrete answer to this question, this …
distribution is adversarially perturbed? To provide a concrete answer to this question, this …
Learning visual question answering on controlled semantic noisy labels
Abstract Visual Question Answering (VQA) has made great progress recently due to the
increasing ability to understand and encode multi-modal inputs based on deep learning …
increasing ability to understand and encode multi-modal inputs based on deep learning …