Related papers: LEAD Dataset: How Can Labels for Sound Event Detec…
Event camera has significant advantages in capturing dynamic scene information while being prone to noise interference, particularly in challenging conditions like low threshold and low illumination. However, most existing research focuses…
Acoustic event detection for content analysis in most cases relies on lots of labeled data. However, manually annotating data is a time-consuming task, which thus makes few annotated resources available so far. Unlike audio event detection,…
Audio Event Detection is an important task for content analysis of multimedia data. Most of the current works on detection of audio events is driven through supervised learning approaches. We propose a weakly supervised learning framework…
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…
Sound Event Localization and Detection (SELD) is crucial in spatial audio processing, enabling systems to detect sound events and estimate their 3D directions. Existing SELD methods use single- or dual-branch architectures: single-branch…
High annotation costs from hiring or crowdsourcing complicate the creation of large, high-quality datasets needed for training reliable text classifiers. Recent research suggests using Large Language Models (LLMs) to automate the annotation…
Modern buildings are densely equipped with smart energy meters, which periodically generate a massive amount of time-series data yielding few million data points every day. This data can be leveraged to discover the underlying loads, infer…
Supervised training of object detectors requires well-annotated large-scale datasets, whose production is costly. Therefore, some efforts have been made to obtain annotations in economical ways, such as cloud sourcing. However, datasets…
In this paper, we introduce a novel knowledge distillation approach for the semantic segmentation task. Unlike previous methods that rely on power-trained teachers or other modalities to provide additional knowledge, our approach does not…
Traditional dataset distillation primarily focuses on image representation while often overlooking the important role of labels. In this study, we introduce Label-Augmented Dataset Distillation (LADD), a new dataset distillation framework…
Obtaining annotations for complex computer vision tasks such as object detection is an expensive and time-intense endeavor involving a large number of human workers or expert opinions. Reducing the amount of annotations required while…
Most user-related data can be represented as a sequence of events associated with a timestamp and a collection of categorical labels. For example, the purchased basket of goods and the time of buying fully characterize the event of the…
Sound event detection (SED) entails two subtasks: recognizing what types of sound events are present in an audio stream (audio tagging), and pinpointing their onset and offset times (localization). In the popular multiple instance learning…
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…
The ranking of sound event detection (SED) systems may be biased by assumptions inherent to evaluation criteria and to the choice of an operating point. This paper compares conventional event-based and segment-based criteria against the…
Prior approaches to lead instrument detection primarily analyze mixture audio, limited to coarse classifications and lacking generalization ability. This paper presents a novel approach to lead instrument detection in multitrack music audio…
Label noise detection has been widely studied in Machine Learning because of its importance in improving training data quality. Satisfactory noise detection has been achieved by adopting ensembles of classifiers. In this approach, an…
Sound event localization and detection (SELD) is an emerging research topic that aims to unify the tasks of sound event detection and direction-of-arrival estimation. As a result, SELD inherits the challenges of both tasks, such as noise,…
Recent studies indicate that deep neural networks degrade in generalization performance under noisy supervision. Existing methods focus on isolating clean subsets or correcting noisy labels, facing limitations such as high computational…
In this paper, we present a method called HODGEPODGE\footnotemark[1] for large-scale detection of sound events using weakly labeled, synthetic, and unlabeled data proposed in the Detection and Classification of Acoustic Scenes and Events…