Related papers: MarginNCE: Robust Sound Localization with a Negati…

Recent investigations in noise contrastive estimation suggest, both empirically as well as theoretically, that while having more "negative samples" in the contrastive loss improves downstream classification performance initially, beyond a…

Adversarial attacks exploit the vulnerabilities of convolutional neural networks by introducing imperceptible perturbations that lead to misclassifications, exposing weaknesses in feature representations and decision boundaries. This paper…

There is extensive interest in metric learning methods for image retrieval. Many metric learning loss functions focus on learning a correct ranking of training samples, but strongly overfit semantically inconsistent labels and require a…

Learning a parametric model of a data distribution is a well-known statistical problem that has seen renewed interest as it is brought to scale in deep learning. Framing the problem as a self-supervised task, where data samples are…

This paper improves contrastive learning for sentence embeddings from two perspectives: handling dropout noise and addressing feature corruption. Specifically, for the first perspective, we identify that the dropout noise from negative…

Most of existing audio fingerprinting systems have limitations to be used for high-specific audio retrieval at scale. In this work, we generate a low-dimensional representation from a short unit segment of audio, and couple this fingerprint…

This paper addresses the problem of localizing audio sources using binaural measurements. We propose a supervised formulation that simultaneously localizes multiple sources at different locations. The approach is intrinsically efficient…

Real-world sound scenes consist of time-varying collections of sound sources, each generating characteristic sound events that are mixed together in audio recordings. The association of these constituent sound events with their mixture and…

Metric learning aims to learn a distance metric such that semantically similar instances are pulled together while dissimilar instances are pushed away. Many existing methods consider maximizing or at least constraining a distance margin in…

Self-supervised learning (SSL) approaches, such as contrastive and generative methods, have advanced environmental sound representation learning using unlabeled data. However, how these approaches can complement each other within a unified…

This paper presents a robust approach for learning from noisy pairwise comparisons. We propose sufficient conditions on the loss function under which the risk minimization framework becomes robust to noise in the pairwise similar dissimilar…

GRPO is a standard approach to endowing pretrained LLMs with reasoning capabilities. It estimates the advantage of an outcome from a group of $K$ outcomes, and promotes those with positive advantages inside a trust region. Since GRPO…

The objective of the sound source localization task is to enable machines to detect the location of sound-making objects within a visual scene. While the audio modality provides spatial cues to locate the sound source, existing approaches…

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…

Sound source localization (SSL) is the task of locating the source of sound within an image. Due to the lack of localization labels, the de facto standard in SSL has been to represent an image and audio as a single embedding vector each,…

Deep learning with noisy labels is an interesting challenge in weakly supervised learning. Despite their significant learning capacity, CNNs have a tendency to overfit in the presence of samples with noisy labels. Alleviating this issue,…

Recently, speech separation (SS) task has achieved remarkable progress driven by deep learning technique. However, it is still challenging to separate target speech from noisy mixture, as the neural model is vulnerable to assign background…

Deep neural network-based classifiers trained with the categorical cross-entropy (CCE) loss are sensitive to label noise in the training data. One common type of method that can mitigate the impact of label noise can be viewed as supervised…

Deep neural networks are able to memorize noisy labels easily with a softmax cross-entropy (CE) loss. Previous studies attempted to address this issue focus on incorporating a noise-robust loss function to the CE loss. However, the…

Noise-contrastive estimation (NCE) is a statistically consistent method for learning unnormalized probabilistic models. It has been empirically observed that the choice of the noise distribution is crucial for NCE's performance. However,…