Related papers: Self-Supervised Representation Learning With MUlti…
This paper presents a performance analysis of the MUltiple SIgnal Classification (MUSIC) algorithm applied on $D$ dimensional single-snapshot spectral estimation while $s$ true frequencies are located on the continuum of a bounded domain.…
A representation technique that allows encoding music in a way that contains musical meaning would improve the results of any model trained for computer music tasks like generation of melodies and harmonies of better quality. The field of…
To learn intrinsic low-dimensional structures from high-dimensional data that most discriminate between classes, we propose the principle of Maximal Coding Rate Reduction ($\text{MCR}^2$), an information-theoretic measure that maximizes the…
We apply MUltiple SIgnal Classification (MUSIC) algorithm for the location reconstruction of a set of {two-dimensional circle-like} small inhomogeneities in the limited-aperture inverse scattering problem. Compared with the full- or…
We propose a novel method for unsupervised semantic image segmentation based on mutual information maximization between local and global high-level image features. The core idea of our work is to leverage recent progress in self-supervised…
Semi-supervised learning has demonstrated great potential in medical image segmentation by utilizing knowledge from unlabeled data. However, most existing approaches do not explicitly capture high-level semantic relations between distant…
In this letter, we formulate a compositional distributed learning framework for multi-view perception by leveraging the maximal coding rate reduction principle combined with subspace basis fusion. In the proposed algorithm, each agent…
Multi-view representation learning aims to capture comprehensive information from multiple views of a shared context. Recent works intuitively apply contrastive learning to different views in a pairwise manner, which is still scalable:…
The high computational complexity of the multiple signal classification (MUSIC) algorithm is mainly caused by the subspace decomposition and spectrum search, especially for frequent real-time applications or massive sensors. In this paper,…
Unsupervised semantic segmentation requires assigning a label to every pixel without any human annotations. Despite recent advances in self-supervised representation learning for individual images, unsupervised semantic segmentation with…
In this work, we study music/video cross-modal recommendation, i.e. recommending a music track for a video or vice versa. We rely on a self-supervised learning paradigm to learn from a large amount of unlabelled data. We rely on a…
Multiple Instance Learning (MIL) has been widely used in weakly supervised whole slide image (WSI) classification. Typical MIL methods include a feature embedding part, which embeds the instances into features via a pre-trained feature…
We investigate the task of retrieving information from compositional distributed representations formed by Hyperdimensional Computing/Vector Symbolic Architectures and present novel techniques which achieve new information rate bounds.…
Sparse coding is an unsupervised learning algorithm that learns a succinct high-level representation of the inputs given only unlabeled data; it represents each input as a sparse linear combination of a set of basis functions. Originally…
Discrete multiple signal classification (MUSIC) with its low computational cost and mild condition requirement becomes a significant noniterative algorithm for joint sparse recovery (JSR). However, it fails in rank defective problem caused…
Training recommender systems for next-item recommendation often requires unique embeddings to be learned for each item, which may take up most of the trainable parameters for a model. Shared embeddings, such as using content information,…
In this work, we present a method for learning interpretable music signal representations directly from waveform signals. Our method can be trained using unsupervised objectives and relies on the denoising auto-encoder model that uses a…
A key aspect of machine learning models lies in their ability to learn efficient intermediate features. However, the input representation plays a crucial role in this process, and polyphonic musical scores remain a particularly complex type…
Training visual embeddings with labeled data supervision has been the de facto setup for representation learning in computer vision. Inspired by recent success of adopting masked image modeling (MIM) in self-supervised representation…
Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies more heavily on…