Related papers: Clustering-based hard negative sampling for superv…

Contrastive learning has achieved remarkable success in learning effective representations, with supervised contrastive learning often outperforming self-supervised approaches. However, in real-world scenarios, data annotations are often…

Sound source localization aims to localize objects emitting the sound in visual scenes. Recent works obtaining impressive results typically rely on contrastive learning. However, the common practice of randomly sampling negatives in prior…

A key requirement for the success of supervised deep learning is a large labeled dataset - a condition that is difficult to meet in medical image analysis. Self-supervised learning (SSL) can help in this regard by providing a strategy to…

Self-supervised representation learning can mitigate the limitations in recognition tasks with few manually labeled data but abundant unlabeled data---a common scenario in sound event research. In this work, we explore unsupervised…

Recent developments in Self-Supervised Learning (SSL) have demonstrated significant potential for Speaker Verification (SV), but closing the performance gap with supervised systems remains an ongoing challenge. SSL frameworks rely on…

This paper shows that a popular approach to the supervised embedding of documents for classification, namely, contrastive Word Mover's Embedding, can be significantly enhanced by adding interpretability. This interpretability is achieved by…

Significant progress has been made in spoken question answering (SQA) in recent years. However, many existing methods, including large audio language models, struggle with processing long audio. Follow the success of retrieval augmented…

Machine hearing of the environmental sound is one of the important issues in the audio recognition domain. It gives the machine the ability to discriminate between the different input sounds that guides its decision making. In this work we…

Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples via a one-vs-many softmax cross-entropy loss. By…

Detecting musical versions (different renditions of the same piece) is a challenging task with important applications. Because of the ground truth nature, existing approaches match musical versions at the track level (e.g., whole song).…

In this paper, we present a time-contrastive learning (TCL) based bottleneck (BN)feature extraction method for speech signals with an application to text-dependent (TD) speaker verification (SV). It is well-known that speech signals exhibit…

Whilst contrastive learning has recently brought notable benefits to deep clustering of unlabelled images by learning sample-specific discriminative visual features, its potential for explicitly inferring class decision boundaries is less…

Face clustering tasks can learn hierarchical semantic information from large-scale data, which has the potential to help facilitate face recognition. However, there are few works on this problem. This paper explores it by proposing a joint…

This work considers supervised contrastive learning for semantic segmentation. We apply contrastive learning to enhance the discriminative power of the multi-scale features extracted by semantic segmentation networks. Our key methodological…

In this paper, we propose Discriminative Neural Clustering (DNC) that formulates data clustering with a maximum number of clusters as a supervised sequence-to-sequence learning problem. Compared to traditional unsupervised clustering…

Semantic representation learning for sentences is an important and well-studied problem in NLP. The current trend for this task involves training a Transformer-based sentence encoder through a contrastive objective with text, i.e.,…

In real-world applications, speaker recognition models often face various domain-mismatch challenges, leading to a significant drop in performance. Although numerous domain adaptation techniques have been developed to address this issue,…

Weakly supervised semantic segmentation (WSSS) has gained significant popularity since it relies only on weak labels such as image level annotations rather than pixel level annotations required by supervised semantic segmentation (SSS)…

Cued Speech (CS) is a communication system for deaf people or hearing impaired people, in which a speaker uses it to aid a lipreader in phonetic level by clarifying potentially ambiguous mouth movements with hand shape and positions.…

Recently, heterogeneous Graph Neural Networks (GNNs) have become a de facto model for analyzing HGs, while most of them rely on a relative large number of labeled data. In this work, we investigate Contrastive Learning (CL), a key component…