Related papers: Decoupling "when to update" from "how to update"
Large datasets often have unreliable labels-such as those obtained from Amazon's Mechanical Turk or social media platforms-and classifiers trained on mislabeled datasets often exhibit poor performance. We present a simple, effective…
Most existing methods that cope with noisy labels usually assume that the class distributions are well balanced, which has insufficient capacity to deal with the practical scenarios where training samples have imbalanced distributions. To…
Learning with noisy labels remains challenging because over-parameterized networks memorize corrupted supervision. Meta-learning-based sample reweighting mitigates this by using a small clean subset to guide training, yet its behavior and…
Learning from noisy labels (LNL) aims to train high-performance deep models using noisy datasets. Meta learning based label correction methods have demonstrated remarkable performance in LNL by designing various meta label rectification…
Deep learning with noisy labels is an interesting challenge in weakly supervised learning. Despite their significant learning capacity, CNNs have a tendency to overfit in the presence of samples with noisy labels. Alleviating this issue,…
It is crucial to distinguish mislabeled samples for dealing with noisy labels. Previous methods such as Coteaching and JoCoR introduce two different networks to select clean samples out of the noisy ones and only use these clean ones to…
Webly supervised learning becomes attractive recently for its efficiency in data expansion without expensive human labeling. However, adopting search queries or hashtags as web labels of images for training brings massive noise that…
Noisy labels damage the performance of deep networks. For robust learning, a prominent two-stage pipeline alternates between eliminating possible incorrect labels and semi-supervised training. However, discarding part of noisy labels could…
Crowdsourcing platforms are often used to collect datasets for training machine learning models, despite higher levels of inaccurate labeling compared to expert labeling. There are two common strategies to manage the impact of such noise.…
Traditional methods for learning with the presence of noisy labels have successfully handled datasets with artificially injected noise but still fall short of adequately handling real-world noise. With the increasing use of meta-learning in…
Training Deep neural networks (DNNs) on noisy labeled datasets is a challenging problem, because learning on mislabeled examples deteriorates the performance of the network. As the ground truth availability is limited with real-world noisy…
Deep neural networks have shown impressive performance in supervised learning, enabled by their ability to fit well to the provided training data. However, their performance is largely dependent on the quality of the training data and often…
The growing importance of massive datasets used for deep learning makes robustness to label noise a critical property for classifiers to have. Sources of label noise include automatic labeling, non-expert labeling, and label corruption by…
Person re-identification (re-ID), is a challenging task due to the high variance within identity samples and imaging conditions. Although recent advances in deep learning have achieved remarkable accuracy in settled scenes, i.e., source…
The challenge of learning with noisy labels is significant in machine learning, as it can severely degrade the performance of prediction models if not addressed properly. This paper introduces a novel framework that conceptualizes noisy…
Noisy labels, inevitably existing in pseudo segmentation labels generated from weak object-level annotations, severely hampers model optimization for semantic segmentation. Previous works often rely on massive hand-crafted losses and…
The task of continual learning requires careful design of algorithms that can tackle catastrophic forgetting. However, the noisy label, which is inevitable in a real-world scenario, seems to exacerbate the situation. While very few studies…
Annotating the dataset with high-quality labels is crucial for performance of deep network, but in real world scenarios, the labels are often contaminated by noise. To address this, some methods were proposed to automatically split clean…
A critical bottleneck in supervised machine learning is the need for large amounts of labeled data which is expensive and time consuming to obtain. However, it has been shown that a small amount of labeled data, while insufficient to…
The drastic increase of data quantity often brings the severe decrease of data quality, such as incorrect label annotations, which poses a great challenge for robustly training Deep Neural Networks (DNNs). Existing learning \mbox{methods}…