Related papers: LOPS: Learning Order Inspired Pseudo-Label Selecti…

Modern deep learning systems are data-hungry. Learning with web data is one of the feasible solutions, but will introduce label noise inevitably, which can hinder the performance of deep neural networks. Sample selection is an effective way…

Neural Encoders are frequently used in the NLP domain to perform dense retrieval tasks, for instance, to generate the candidate documents for a given query in question-answering tasks. However, sparse annotation and label noise in the…

Supervised deep learning requires a large amount of training samples with annotations (e.g. label class for classification task, pixel- or voxel-wised label map for segmentation tasks), which are expensive and time-consuming to obtain.…

Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance. To relieve this issue, curriculum learning is proposed to improve model performance and…

Deep neural networks tend to memorize noisy labels, severely degrading their generalization performance. Although Mixup has demonstrated effectiveness in improving generalization and robustness, existing Mixup-based methods typically…

Self-supervised vision transformers (SSTs) have shown great potential to yield rich localization maps that highlight different objects in an image. However, these maps remain class-agnostic since the model is unsupervised. They often tend…

Noise in data appears to be inevitable in most real-world machine learning applications and would cause severe overfitting problems. Not only can data features contain noise, but labels are also prone to be noisy due to human input. In this…

Recent research has revealed that deep neural networks often take dataset biases as a shortcut to make decisions rather than understand tasks, leading to failures in real-world applications. In this study, we focus on the spurious…

Label-noise learning (LNL) aims to increase the model's generalization given training data with noisy labels. To facilitate practical LNL algorithms, researchers have proposed different label noise types, ranging from class-conditional to…

Datasets with noisy labels are a common occurrence in practical applications of classification methods. We propose a simple probabilistic method for training deep classifiers under input-dependent (heteroscedastic) label noise. We assume an…

Training deep neural networks requires massive amounts of training data, but for many tasks only limited labeled data is available. This makes weak supervision attractive, using weak or noisy signals like the output of heuristic methods or…

Fine tuning self supervised pretrained models using pseudo labels can effectively improve speech recognition performance. But, low quality pseudo labels can misguide decision boundaries and degrade performance. We propose a simple yet…

While semi-supervised learning (SSL) has yielded promising results, the more realistic SSL scenario remains to be explored, in which the unlabeled data exhibits extremely high recognition difficulty, e.g., fine-grained visual classification…

Deep neural networks trained with standard cross-entropy loss are more prone to memorize noisy labels, which degrades their performance. Negative learning using complementary labels is more robust when noisy labels intervene but with an…

Many real-world applications involve the use of Optical Character Recognition (OCR) engines to transform handwritten images into transcripts on which downstream Natural Language Processing (NLP) models are applied. In this process, OCR…

Noisy labels are very common in deep supervised learning. Although many studies tend to improve the robustness of deep training for noisy labels, rare works focus on theoretically explaining the training behaviors of learning with noisily…

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 high-quality labels in many real-world scenarios. As noisy…

Localizing keypoints of an object is a basic visual problem. However, supervised learning of a keypoint localization network often requires a large amount of data, which is expensive and time-consuming to obtain. To remedy this, there is an…

We introduce a novel method for training machine learning models in the presence of noisy labels, which are prevalent in domains such as medical diagnosis and autonomous driving and have the potential to degrade a model's generalization…

Sample selection approaches are popular in robust learning from noisy labels. However, how to properly control the selection process so that deep networks can benefit from the memorization effect is a hard problem. In this paper, motivated…