相关论文: Chord Label Personalization through Deep Learning …

Falsely annotated samples, also known as noisy labels, can significantly harm the performance of deep learning models. Two main approaches for learning with noisy labels are global noise estimation and data filtering. Global noise…

Annotators exhibit disagreement during data labeling, which can be termed as annotator label uncertainty. Annotator label uncertainty manifests in variations of labeling quality. Training with a single low-quality annotation per sample…

Audio Chord Estimation (ACE) holds a pivotal role in music information research, having garnered attention for over two decades due to its relevance for music transcription and analysis. Despite notable advancements, challenges persist in…

Many tasks in natural language processing involve predicting structured outputs, e.g., sequence labeling, semantic role labeling, parsing, and machine translation. Researchers are increasingly applying deep representation learning to these…

While deep learning has achieved significant advances in accuracy for medical image segmentation, its benefits for deformable image registration have so far remained limited to reduced computation times. Previous work has either focused on…

We discuss training techniques, objectives and metrics toward personalization of deep learning models. In machine learning, personalization addresses the goal of a trained model to target a particular individual by optimizing one or more…

Creating datasets manually by human annotators is a laborious task that can lead to biased and inhomogeneous labels. We propose a flexible, semi-automatic framework for labeling data for relation extraction. Furthermore, we provide a…

Sequence classification is the task of predicting a class label given a sequence of observations. In many applications such as healthcare monitoring or intrusion detection, early classification is crucial to prompt intervention. In this…

As medical datasets rapidly expand, creating detailed annotations of different body structures becomes increasingly expensive and time-consuming. We consider that requesting radiologists to create detailed annotations is unnecessarily…

Vision-Language Models (VLMs), with their powerful content generation capabilities, have been successfully applied to data annotation processes. However, the VLM-generated labels exhibit dual limitations: low quality (i.e., label noise) and…

Multi-pitch estimation is a decades-long research problem involving the detection of pitch activity associated with concurrent musical events within multi-instrument mixtures. Supervised learning techniques have demonstrated solid…

This work studies semantic segmentation using 3D LiDAR data. Popular deep learning methods applied for this task require a large number of manual annotations to train the parameters. We propose a new method that makes full use of the…

Many music AI models learn a map between music content and human-defined labels. However, many annotations, such as chords, can be naturally expressed within the music modality itself, e.g., as sequences of symbolic notes. This observation…

Automatically assessing emotional valence in human speech has historically been a difficult task for machine learning algorithms. The subtle changes in the voice of the speaker that are indicative of positive or negative emotional states…

Many machine learning tasks -- particularly those in affective computing -- are inherently subjective. When asked to classify facial expressions or to rate an individual's attractiveness, humans may disagree with one another, and no single…

Contrastive learning methods enforce label distance relationships in feature space to improve representation capability for regression models. However, these methods highly depend on label information to correctly recover ordinal…

Multi-rater medical image segmentation captures the inherent ambiguity of clinical interpretation, where diagnostic boundaries vary across experts and imaging devices. Existing approaches often reduce this diversity to consensus labels or…

Audio impairment recognition is based on finding noise in audio files and categorising the impairment type. Recently, significant performance improvement has been obtained thanks to the usage of advanced deep learning models. However,…

Aggregating multiple annotations into a single ground truth label may hide valuable insights into annotator disagreement, particularly in tasks where subjectivity plays a crucial role. In this work, we explore methods for identifying…

State-of-the-art speaker verification systems are inherently dependent on some kind of human supervision as they are trained on massive amounts of labeled data. However, manually annotating utterances is slow, expensive and not scalable to…