Related papers: Addressing Missing Labels in Large-Scale Sound Eve…

For classification tasks, deep neural networks are prone to overfitting in the presence of label noise. Although existing methods are able to alleviate this problem at low noise levels, they encounter significant performance reduction at…

Pseudo-label learning methods have been widely applied in weakly-supervised temporal action localization. Existing works directly utilize weakly-supervised base model to generate instance-level pseudo-labels for training the…

Real-world datasets commonly have noisy labels, which negatively affects the performance of deep neural networks (DNNs). In order to address this problem, we propose a label noise robust learning algorithm, in which the base classifier is…

To reveal the importance of temporal precision in ground truth audio event labels, we collected precise (~0.1 sec resolution) "strong" labels for a portion of the AudioSet dataset. We devised a temporally strong evaluation set (including…

In self-supervised learning for speaker recognition, pseudo labels are useful as the supervision signals. It is a known fact that a speaker recognition model doesn't always benefit from pseudo labels due to their unreliability. In this…

Multi-modal learning in the audio-language domain has seen significant advancements in recent years. However, audio-language learning faces challenges due to limited and lower-quality data compared to image-language tasks. Existing…

We approach the problem of improving robustness of deep learning algorithms in the presence of label noise. Building upon existing label correction and co-teaching methods, we propose a novel training procedure to mitigate the memorization…

The Detection and Classification of Acoustic Scenes and Events Challenge Task 4 aims to advance sound event detection (SED) systems in domestic environments by leveraging training data with different supervision uncertainty. Participants…

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…

To discover intrinsic inter-class transition probabilities underlying data, learning with noise transition has become an important approach for robust deep learning on corrupted labels. Prior methods attempt to achieve such transition…

The availability of large labeled datasets has allowed Convolutional Network models to achieve impressive recognition results. However, in many settings manual annotation of the data is impractical; instead our data has noisy labels, i.e.…

The availability of a large quantity of labelled training data is crucial for the training of modern object detectors. Hand labelling training data is time consuming and expensive while automatic labelling methods inevitably add unwanted…

Engagement recognition in video datasets, unlike traditional image classification tasks, is particularly challenged by subjective labels and noise limiting model performance. To overcome the challenges of subjective and noisy engagement…

This study explores the robustness of label noise classifiers, aiming to enhance model resilience against noisy data in complex real-world scenarios. Label noise in supervised learning, characterized by erroneous or imprecise labels,…

While deep learning has been incredibly successful in modeling tasks with large, carefully curated labeled datasets, its application to problems with limited labeled data remains a challenge. The aim of the present work is to improve the…

Current audio classification models have small class vocabularies relative to the large number of sound event classes of interest in the real world. Thus, they provide a limited view of the world that may miss important yet unexpected or…

Deep neural networks have proven to be highly effective when large amounts of data with clean labels are available. However, their performance degrades when training data contains noisy labels, leading to poor generalization on the test…

Learning with noisy labels has gained increasing attention because the inevitable imperfect labels in real-world scenarios can substantially hurt the deep model performance. Recent studies tend to regard low-loss samples as clean ones and…

In the last couple of years, weakly labeled learning has turned out to be an exciting approach for audio event detection. In this work, we introduce webly labeled learning for sound events which aims to remove human supervision altogether…

Most studies on learning from noisy labels rely on unrealistic models of i.i.d. label noise, such as class-conditional transition matrices. More recent work on instance-dependent noise models are more realistic, but assume a single…