Related papers: Generalized Jensen-Shannon Divergence Loss for Lea…
Designing robust loss functions is popular in learning with noisy labels while existing designs did not explicitly consider the overfitting property of deep neural networks (DNNs). As a result, applying these losses may still suffer from…
This paper studies a family of estimators based on noise-contrastive estimation (NCE) for learning unnormalized distributions. The main contribution of this work is to provide a unified perspective on various methods for learning…
Deep learning has made many remarkable achievements in many fields but suffers from noisy labels in datasets. The state-of-the-art learning with noisy label method Co-teaching and Co-teaching+ confronts the noisy label by mutual-information…
Single-channel speech enhancement with deep neural networks (DNNs) has shown promising performance and is thus intensively being studied. In this paper, instead of applying the mean squared error (MSE) as the loss function during DNN…
Learning exists in the context of data, yet notions of confidence typically focus on model predictions, not label quality. Confident learning (CL) is an alternative approach which focuses instead on label quality by characterizing and…
As sound event classification moves towards larger datasets, issues of label noise become inevitable. Web sites can supply large volumes of user-contributed audio and metadata, but inferring labels from this metadata introduces errors due…
Node classification on graphs is a significant task with a wide range of applications, including social analysis and anomaly detection. Even though graph neural networks (GNNs) have produced promising results on this task, current…
Accurately annotating large scale dataset is notoriously expensive both in time and in money. Although acquiring low-quality-annotated dataset can be much cheaper, it often badly damages the performance of trained models when using such…
Since deep neural networks are over-parameterized, they can memorize noisy examples. We address such a memorization issue in the presence of label noise. From the fact that deep neural networks cannot generalize to neighborhoods of…
Brain lesion and anatomy segmentation in magnetic resonance images are fundamental tasks in neuroimaging research and clinical practice. Given enough training data, convolutional neuronal networks (CNN) proved to outperform all existent…
The deep model training procedure requires large-scale datasets of annotated data. Due to the difficulty of annotating a large number of samples, label noise caused by incorrect annotations is inevitable, resulting in low model performance…
Kernel embeddings of distributions and the Maximum Mean Discrepancy (MMD), the resulting distance between distributions, are useful tools for fully nonparametric two-sample testing and learning on distributions. However, it is rarely that…
Researches using margin based comparison loss demonstrate the effectiveness of penalizing the distance between face feature and their corresponding class centers. Despite their popularity and excellent performance, they do not explicitly…
Learning with labels noise has gained significant traction recently due to the sensitivity of deep neural networks under label noise under common loss functions. Losses that are theoretically robust to label noise, however, often makes…
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…
Training data collected in the wild often contain noisy labels and outliers that substantially degrade the performance and reliability of deep neural networks. While data cleaning is commonly applied as a separate preprocessing stage, such…
State-of-the-art anomalous sound detection systems often utilize angular margin losses to learn suitable representations of acoustic data using an auxiliary task, which usually is a supervised or self-supervised classification task. The…
Due to the limitation of strong-labeled sound event detection data set, using synthetic data to improve the sound event detection system performance has been a new research focus. In this paper, we try to exploit the usage of synthetic data…
Despite the deep neural networks (DNN) has achieved excellent performance in image classification researches, the training of DNNs needs a large of clean data with accurate annotations. The collect of a dataset is easy, but it is difficult…
The rise of machine learning in image processing has created a gap between trainable data-driven and classical model-driven approaches: While learning-based models often show superior performance, classical ones are often more transparent.…