Related papers: Drainage: A Unifying Framework for Addressing Clas…

The prevalence of noisy labels in real-world datasets poses a significant impediment to the effective deployment of deep learning models. While meta-learning strategies have emerged as a promising approach for addressing this challenge,…

Calibration of neural networks is a topical problem that is becoming more and more important as neural networks increasingly underpin real-world applications. The problem is especially noticeable when using modern neural networks, for which…

Label noise and ambiguities between similar classes are challenging problems in developing new models and annotating new data for semantic segmentation. In this paper, we propose Compensation Learning in Semantic Segmentation, a framework…

To improve trust and transparency, it is crucial to be able to interpret the decisions of Deep Neural classifiers (DNNs). Instance-level examinations, such as attribution techniques, are commonly employed to interpret the model decisions.…

In many real-world classification problems, the labels of training examples are randomly corrupted. Most previous theoretical work on classification with label noise assumes that the two classes are separable, that the label noise is…

A recurring focus of the deep learning community is towards reducing the labeling effort. Data gathering and annotation using a search engine is a simple alternative to generating a fully human-annotated and human-gathered dataset. Although…

Deep neural networks (DNNs) have achieved great success in a wide variety of medical image analysis tasks. However, these achievements indispensably rely on the accurately-annotated datasets. If with the noisy-labeled images, the training…

Large-scale datasets possessing clean label annotations are crucial for training Convolutional Neural Networks (CNNs). However, labeling large-scale data can be very costly and error-prone, and even high-quality datasets are likely to…

Distantly supervised named entity recognition (DS-NER) efficiently reduces labor costs but meanwhile intrinsically suffers from the label noise due to the strong assumption of distant supervision. Typically, the wrongly labeled instances…

In many domains, collecting sufficient labeled training data for supervised machine learning requires easily accessible but noisy sources, such as crowdsourcing services or tagged Web data. Noisy labels occur frequently in data sets…

Network traffic classification, particularly elephant flow detection, faces significant challenges when deployed across heterogeneous network environments. While existing approaches demonstrate high accuracy within single domains, they…

We consider the problem of training a model under the presence of label noise. Current approaches identify samples with potentially incorrect labels and reduce their influence on the learning process by either assigning lower weights to…

Learning from noisy labels (LNL) is crucial in deep learning, in which one of the approaches is to identify clean-label samples from poorly-annotated datasets. Such an identification is challenging because the conventional LNL problem,…

Modern deep neural networks can easily overfit to biased training data containing corrupted labels or class imbalance. Sample re-weighting methods are popularly used to alleviate this data bias issue. Most current methods, however, require…

Deep learning approaches to anomaly detection have recently improved the state of the art in detection performance on complex datasets such as large collections of images or text. These results have sparked a renewed interest in the anomaly…

Multi-view learning methods often focus on improving decision accuracy while neglecting the decision uncertainty, which significantly restricts their applications in safety-critical scenarios. To address this, trusted multi-view learning…

To collect large scale annotated data, it is inevitable to introduce label noise, i.e., incorrect class labels. To be robust against label noise, many successful methods rely on the noisy classifiers (i.e., models trained on the noisy…

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…

In learning with noisy labels, the sample selection approach is very popular, which regards small-loss data as correctly labeled during training. However, losses are generated on-the-fly based on the model being trained with noisy labels,…

Existing deep active learning algorithms achieve impressive sampling efficiency on natural language processing tasks. However, they exhibit several weaknesses in practice, including (a) inability to use uncertainty sampling with black-box…