Related papers: Learning to Discover: A Generalized Framework for …

Retrieval-Augmented Generation (RAG) systems traditionally treat retrieval and generation as separate processes, requiring explicit textual queries to connect them. This separation can limit the ability of models to generalize across…

The rapid development of large language models has led to the widespread adoption of Retrieval-Augmented Generation (RAG), which integrates external knowledge to alleviate knowledge bottlenecks and mitigate hallucinations. However, the…

An important goal of medical imaging is to be able to precisely detect patterns of disease specific to individual scans; however, this is challenged in brain imaging by the degree of heterogeneity of shape and appearance. Traditional…

Most modern neural networks for classification fail to take into account the concept of the unknown. Trained neural networks are usually tested in an unrealistic scenario with only examples from a closed set of known classes. In an attempt…

The ability to accurately recognize, localize and separate sound sources is fundamental to any audio-visual perception task. Historically, these abilities were tackled separately, with several methods developed independently for each task.…

Prior approaches to lead instrument detection primarily analyze mixture audio, limited to coarse classifications and lacking generalization ability. This paper presents a novel approach to lead instrument detection in multitrack music audio…

In this work, we address the challenging task of long-tailed image recognition. Previous long-tailed recognition methods commonly focus on the data augmentation or re-balancing strategy of the tail classes to give more attention to tail…

Graph autoencoders (GAE) and variational graph autoencoders (VGAE) emerged as two powerful groups of unsupervised node embedding methods, with various applications to graph-based machine learning problems such as link prediction and…

One of the key limitations of modern deep learning approaches lies in the amount of data required to train them. Humans, by contrast, can learn to recognize novel categories from just a few examples. Instrumental to this rapid learning…

Retrieval-Augmented Generation (RAG) has emerged as a key paradigm for enhancing large language models (LLMs) by incorporating external knowledge. However, current RAG methods face two limitations: (1) they only cover limited RAG scenarios.…

Face recognition has advanced considerably with the availability of large-scale labeled datasets. However, how to further improve the performance with the easily accessible unlabeled dataset remains a challenge. In this paper, we propose…

Open-Set Domain Generalization (OSDG) aims to enable deep learning models to recognize unseen categories in new domains, which is crucial for real-world applications. Label noise hinders open-set domain generalization by corrupting…

Music auto-tagging is essential for organizing and discovering music in extensive digital libraries. While foundation models achieve exceptional performance in this domain, their outputs often lack interpretability, limiting trust and…

This paper presents a summary of the 2019 Unconstrained Ear Recognition Challenge (UERC), the second in a series of group benchmarking efforts centered around the problem of person recognition from ear images captured in uncontrolled…

Generalized Category Discovery is a crucial real-world task. Despite the improved performance on known categories, current methods perform poorly on novel categories. We attribute the poor performance to two reasons: biased knowledge…

Domain generalization (DG) aims to help models trained on a set of source domains generalize better on unseen target domains. The performances of current DG methods largely rely on sufficient labeled data, which are usually costly or…

Learning visual features from unlabeled image data is an important yet challenging task, which is often achieved by training a model on some annotation-free information. We consider spatial contexts, for which we solve so-called jigsaw…

As AI models are trained on ever-expanding datasets, the ability to remove the influence of specific data from trained models has become essential for privacy protection and regulatory compliance. Unlearning addresses this challenge by…

We demonstrate that language models pre-trained on codified (discretely-encoded) music audio learn representations that are useful for downstream MIR tasks. Specifically, we explore representations from Jukebox (Dhariwal et al. 2020): a…

A raga is a melodic structure with fixed notes and a set of rules characterizing a certain mood endorsed through performance. By a vadi swar is meant that note which plays the most significant role in expressing the raga. A samvadi swar…