相关论文: DDSC: Dynamic Dual-Signal Curriculum for Data-Effi…

Semi-supervised learning reduces the costly manual annotation burden in medical image segmentation. A popular approach is the mean teacher (MT) strategy, which applies consistency regularization using a temporally averaged teacher model. In…

In this paper, we present a deep neural network (DNN)-based acoustic scene classification framework. Two hierarchical learning methods are proposed to improve the DNN baseline performance by incorporating the hierarchical taxonomy…

Acoustic scene classification (ASC) and sound event detection (SED) are fundamental tasks in environmental sound analysis, and many methods based on deep learning have been proposed. Considering that information on acoustic scenes and sound…

Sound event detection is a challenging task, especially for scenes with multiple simultaneous events. While event classification methods tend to be fairly accurate, event localization presents additional challenges, especially when large…

Diffusion large language models (dLLMs) have emerged as a promising alternative for text generation, distinguished by their native support for parallel decoding. In practice, block inference is crucial for avoiding order misalignment in…

Generalization under the distribution shift has been a great challenge in computer vision. The prevailing practice of directly employing the one-hot labels as the training targets in domain generalization~(DG) can lead to gradient…

Annotating time boundaries of sound events is labor-intensive, limiting the scalability of strongly supervised learning in audio detection. To reduce annotation costs, weakly-supervised learning with only clip-level labels has been widely…

A challenging problem in deep learning-based machine listening field is the degradation of the performance when using data from unseen conditions. In this paper we focus on the acoustic scene classification (ASC) task and propose an…

Audio tagging aims to perform multi-label classification on audio chunks and it is a newly proposed task in the Detection and Classification of Acoustic Scenes and Events 2016 (DCASE 2016) challenge. This task encourages research efforts to…

This study presents a deep-learning framework for controlling multichannel acoustic feedback in audio devices. Traditional digital signal processing methods struggle with convergence when dealing with highly correlated noise such as…

The remarkable success of contrastive-learning-based multimodal models has been greatly driven by training on ever-larger datasets with expensive compute consumption. Sample selection as an alternative efficient paradigm plays an important…

In unsupervised person Re-ID, peer-teaching strategy leveraging two networks to facilitate training has been proven to be an effective method to deal with the pseudo label noise. However, training two networks with a set of noisy pseudo…

Physical computing has the potential to enable widespread embodied intelligence by leveraging the intrinsic dynamics of complex systems for efficient sensing, processing, and interaction. While individual devices provide basic data…

Conditional diffusion models have shown remarkable performance in various generative tasks, but training them requires large-scale datasets that often contain noise in conditional inputs, a.k.a. noisy labels. This noise leads to condition…

Acoustic scene classification (ASC) predominantly relies on supervised approaches. However, acquiring labeled data for training ASC models is often costly and time-consuming. Recently, self-supervised learning (SSL) has emerged as a…

Curriculum Learning (CL) is a meta-learning paradigm that trains a model by feeding the data instances incrementally according to a schedule, which is based on difficulty progression. Defining meaningful difficulty assessment measures is…

In conventional sound event detection (SED) models, two types of events, namely, those that are present and those that do not occur in an acoustic scene, are regarded as the same type of events. The conventional SED methods cannot…

Dataset Condensation (DC) has emerged as a promising solution to mitigate the computational and storage burdens associated with training deep learning models. However, existing DC methods largely overlook the multi-domain nature of modern…

Datasets with significant proportions of noisy (incorrect) class labels present challenges for training accurate Deep Neural Networks (DNNs). We propose a new perspective for understanding DNN generalization for such datasets, by…

Cognitive Diagnosis (CD) aims to evaluate students' cognitive states based on their interaction data, enabling downstream applications such as exercise recommendation and personalized learning guidance. However, existing methods often…