Related papers: Underdetermined source separation using a sparse S…
Pretrained language models have led to significant performance gains in many NLP tasks. However, the intensive computing resources to train such models remain an issue. Knowledge distillation alleviates this problem by learning a…
Modern smart glasses leverage advanced audio sensing and machine learning technologies to offer real-time transcribing and captioning services, considerably enriching human experiences in daily communications. However, such systems…
To reduce annotation labor associated with object detection, an increasing number of studies focus on transferring the learned knowledge from a labeled source domain to another unlabeled target domain. However, existing methods assume that…
Discrete diffusion models generate structured sequences by progressively unmasking tokens, but enforcing global property constraints during generation remains an open challenge. We propose primal-dual guided decoding, an inference-time…
Though feature-alignment based Domain Adaptive Object Detection (DAOD) methods have achieved remarkable progress, they ignore the source bias issue, i.e., the detector tends to acquire more source-specific knowledge, impeding its…
We present the source separation framework SCARLET for multi-band images, which is based on a generalization of the Non-negative Matrix Factorization to alternative and several simultaneous constraints. Our approach describes the observed…
Dataset distillation (DD) aims to compress large-scale datasets into compact synthetic counterparts for efficient model training. However, existing DD methods exhibit substantial performance degradation on long-tailed datasets. We identify…
In automatic target recognition (ATR) systems, sensors may fail to capture discriminative, fine-grained detail features due to environmental conditions, noise created by CMOS chips, occlusion, parallaxes, and sensor misalignment. Therefore,…
The problem of source localization with ad hoc microphone networks in noisy and reverberant enclosures, given a training set of prerecorded measurements, is addressed in this paper. The training set is assumed to consist of a limited number…
The problem of unsupervised learning and segmentation of hyperspectral images is a significant challenge in remote sensing. The high dimensionality of hyperspectral data, presence of substantial noise, and overlap of classes all contribute…
This work presents a mathematical model to enable rapid prediction of airborne contaminant transport based on scarce sensor measurements. The method is designed for applications in critical infrastructure protection (CIP), such as…
Spatially resolving two incoherent point sources whose separation is well below the diffraction limit dictated by classical optics has recently been shown possible using techniques that decompose the incoming radiation into orthogonal…
In general, multi-channel source separation has utilized inter-microphone phase differences (IPDs) concatenated with magnitude information in time-frequency domain, or real and imaginary components stacked along the channel axis. However,…
The acoustic scattering problem is modeled by the exterior Helmholtz equation, which is challenging to solve due to both the unboundedness of the domain and the high dispersion error, known as the pollution effect. We develop high-order…
Given recent advances in deep music source separation, we propose a feature representation method that combines source separation with a state-of-the-art representation learning technique that is suitably repurposed for computer audition…
Accurately localizing multiple sources is a critical task with various applications in wireless communications, such as emergency services, including natural post-disaster search and rescue operations. However, scenarios where the receiver…
How to visually localize multiple sound sources in unconstrained videos is a formidable problem, especially when lack of the pairwise sound-object annotations. To solve this problem, we develop a two-stage audiovisual learning framework…
In addition to finding meaningful clusters, centroid-based clustering algorithms such as K-means or mean-shift should ideally find centroids that are valid patterns in the input space, representative of data in their cluster. This is…
Learning how objects sound from video is challenging, since they often heavily overlap in a single audio channel. Current methods for visually-guided audio source separation sidestep the issue by training with artificially mixed video…
A blind source separation method is described to extract sources from data mixtures where the underlying sources are assumed to be sparse and uncorrelated. The approach used is to detect and analyse segments of time where one source exists…