Related papers: Multi-Source Contrastive Learning from Musical Aud…

Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without…

Recent advances have been witnessed in audio-language joint learning, such as CLAP, that shows much success in multi-modal understanding tasks. These models usually aggregate uni-modal local representations, namely frame or word features,…

Music recommender systems frequently utilize network-based models to capture relationships between music pieces, artists, and users. Although these relationships provide valuable insights for predictions, new music pieces or artists often…

We study a novel neural architecture and its training strategies of speaker encoder for speaker recognition without using any identity labels. The speaker encoder is trained to extract a fixed-size speaker embedding from a spoken utterance…

Contrastive learning has become one of the most impressive approaches for multi-modal representation learning. However, previous multi-modal works mainly focused on cross-modal understanding, ignoring in-modal contrastive learning, which…

Traditional music search engines rely on retrieval methods that match natural language queries with music metadata. There have been increasing efforts to expand retrieval methods to consider the audio characteristics of music itself, using…

Audio self-supervised learning (SSL) aims to learn general-purpose representations from large-scale unlabeled audio data. While recent advances have been driven mainly by generative reconstruction objectives, contrastive approaches remain…

With the advent of big data across multiple high-impact applications, we are often facing the challenge of complex heterogeneity. The newly collected data usually consist of multiple modalities and are characterized with multiple labels,…

Visual contrastive learning aims to learn representations by contrasting similar (positive) and dissimilar (negative) pairs of data samples. The design of these pairs significantly impacts representation quality, training efficiency, and…

Inspired by the idea of Positive-incentive Noise (Pi-Noise or $\pi$-Noise) that aims at learning the reliable noise beneficial to tasks, we scientifically investigate the connection between contrastive learning and $\pi$-noise in this…

Counterfactually Augmented Data (CAD) involves creating new data samples by applying minimal yet sufficient modifications to flip the label of existing data samples to other classes. Training with CAD enhances model robustness against…

Contrastive learning is a recent promising approach in unsupervised representation learning where a feature representation of data is learned by solving a pseudo classification problem from unlabelled data. However, it is not…

Recently, contrastive learning approaches (e.g., CLIP (Radford et al., 2021)) have received huge success in multimodal learning, where the model tries to minimize the distance between the representations of different views (e.g., image and…

Contrastive learning -- a modern approach to extract useful representations from unlabeled data by training models to distinguish similar samples from dissimilar ones -- has driven significant progress in foundation models. In this work, we…

We present Contrastive Neighborhood Alignment (CNA), a manifold learning approach to maintain the topology of learned features whereby data points that are mapped to nearby representations by the source (teacher) model are also mapped to…

Learning an effective representation in multi-label text classification (MLTC) is a significant challenge in NLP. This challenge arises from the inherent complexity of the task, which is shaped by two key factors: the intricate connections…

Deep convolutional neural networks have considerably improved state-of-the-art results for semantic segmentation. Nevertheless, even modern architectures lack the ability to generalize well to a test dataset that originates from a different…

Methods based on supervised learning using annotations in an end-to-end fashion have been the state-of-the-art for classification problems. However, they may be limited in their generalization capability, especially in the low data regime.…

Contrastive learning (CL) has shown impressive advances in image representation learning in whichever supervised multi-class classification or unsupervised learning. However, these CL methods fail to be directly adapted to multi-label image…

Self-supervised learning (SSL) offers a powerful way to learn robust, generalizable representations without labeled data. In music, where labeled data is scarce, existing SSL methods typically use generated supervision and multi-view…