中文
相关论文

相关论文: Leave-One-EquiVariant: Alleviating invariance-rela…

200 篇论文

Recent advancements in self-supervised audio-visual representation learning have demonstrated its potential to capture rich and comprehensive representations. However, despite the advantages of data augmentation verified in many learning…

机器学习 · 计算机科学 2024-06-21 Jongsuk Kim , Hyeongkeun Lee , Kyeongha Rho , Junmo Kim , Joon Son Chung

Invariant Contrastive Learning (ICL) methods have achieved impressive performance across various domains. However, the absence of latent space representation for distortion (augmentation)-related information in the latent space makes ICL…

Learning invariant representations is a critical first step in a number of machine learning tasks. A common approach corresponds to the so-called information bottleneck principle in which an application dependent function of mutual…

机器学习 · 计算机科学 2021-02-17 Aditya Kumar Akash , Vishnu Suresh Lokhande , Sathya N. Ravi , Vikas Singh

Recent self-supervised contrastive methods have been able to produce impressive transferable visual representations by learning to be invariant to different data augmentations. However, these methods implicitly assume a particular set of…

计算机视觉与模式识别 · 计算机科学 2021-03-22 Tete Xiao , Xiaolong Wang , Alexei A. Efros , Trevor Darrell

Modeling various aspects that make a music piece unique is a challenging task, requiring the combination of multiple sources of information. Deep learning is commonly used to obtain representations using various sources of information, such…

声音 · 计算机科学 2021-04-05 Andres Ferraro , Xavier Favory , Konstantinos Drossos , Yuntae Kim , Dmitry Bogdanov

Creating representations of shapes that are invari-ant to isometric or almost-isometric transforma-tions has long been an area of interest in shape anal-ysis, since enforcing invariance allows the learningof more effective and robust shape…

计算机视觉与模式识别 · 计算机科学 2021-07-09 Jeffrey Gu , Serena Yeung

We focus on contrastive methods for self-supervised video representation learning. A common paradigm in contrastive learning is to construct positive pairs by sampling different data views for the same instance, with different data…

计算机视觉与模式识别 · 计算机科学 2021-08-23 Chen Sun , Arsha Nagrani , Yonglong Tian , Cordelia Schmid

A data augmentation module is utilized in contrastive learning to transform the given data example into two views, which is considered essential and irreplaceable. However, the predetermined composition of multiple data augmentations brings…

计算机视觉与模式识别 · 计算机科学 2022-08-23 Junbo Zhang , Kaisheng Ma

Several automatic approaches for objective music performance assessment (MPA) have been proposed in the past, however, existing systems are not yet capable of reliably predicting ratings with the same accuracy as professional judges. This…

声音 · 计算机科学 2021-08-16 Pavan Seshadri , Alexander Lerch

Self-supervised visual representation methods are closing the gap with supervised learning performance. These methods rely on maximizing the similarity between embeddings of related synthetic inputs created through data augmentations. This…

机器学习 · 计算机科学 2023-06-09 Alexandre Devillers , Mathieu Lefort

Music retrieval and recommendation applications often rely on content features encoded as embeddings, which provide vector representations of items in a music dataset. Numerous complementary embeddings can be derived from processing items…

信息检索 · 计算机科学 2023-08-15 Andres Ferraro , Jaehun Kim , Sergio Oramas , Andreas Ehmann , Fabien Gouyon

The common research goal of self-supervised learning is to extract a general representation which an arbitrary downstream task would benefit from. In this work, we investigate music audio representation learned from different contrastive…

声音 · 计算机科学 2022-07-12 Jeong Choi , Seongwon Jang , Hyunsouk Cho , Sehee Chung

Self-supervised learning converts raw perceptual data such as images to a compact space where simple Euclidean distances measure meaningful variations in data. In this paper, we extend this formulation by adding additional geometric…

机器学习 · 计算机科学 2023-06-27 Sharut Gupta , Joshua Robinson , Derek Lim , Soledad Villar , Stefanie Jegelka

Recent years have witnessed the effectiveness of contrastive learning in obtaining the representation of dataset that is useful in interpretation and downstream tasks. However, the mechanism that describes this effectiveness have not been…

机器学习 · 统计学 2022-10-17 Masanori Koyama , Takeru Miyato , Kenji Fukumizu

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).…

声音 · 计算机科学 2025-05-19 Joan Serrà , R. Oguz Araz , Dmitry Bogdanov , Yuki Mitsufuji

Recent advances in self-supervised learning (SSL) methods offer a range of strategies for capturing useful representations from music audio without the need for labeled data. While some techniques focus on preserving comprehensive details…

声音 · 计算机科学 2025-08-01 Julia Wilkins , Sivan Ding , Magdalena Fuentes , Juan Pablo Bello

Contrastive learning has gained popularity and pushes state-of-the-art performance across numerous large-scale benchmarks. In contrastive learning, the contrastive loss function plays a pivotal role in discerning similarities between…

计算机视觉与模式识别 · 计算机科学 2025-12-03 Haojin Deng , Yimin Yang

Music Cover Retrieval, also known as Version Identification, aims to recognize distinct renditions of the same underlying musical work, a task central to catalog management, copyright enforcement, and music retrieval. State-of-the-art…

Aiming at exploiting the rich information in user behaviour sequences, sequential recommendation has been widely adopted in real-world recommender systems. However, current methods suffer from the following issues: 1) sparsity of user-item…

信息检索 · 计算机科学 2022-12-06 Yu Wang , Hengrui Zhang , Zhiwei Liu , Liangwei Yang , Philip S. Yu

Efficient inference of large language models (LLMs) is hindered by an ever-growing key-value (KV) cache, making KV cache compression a critical research direction. Traditional methods selectively evict less important KV cache entries, which…

机器学习 · 计算机科学 2025-12-01 Yuxuan Tian , Zihan Wang , Yebo Peng , Aomufei Yuan , Zhiming Wang , Bairen Yi , Xin Liu , Yong Cui , Tong Yang
‹ 上一页 1 2 3 10 下一页 ›