Related papers: STARS: Sensor-agnostic Transformer Architecture fo…
Spectral graph neural networks (GNNs) learn graph representations via spectral-domain graph convolutions. However, most existing spectral graph filters are scalar-to-scalar functions, i.e., mapping a single eigenvalue to a single filtered…
We describe a novel method for blind, single-image spectral super-resolution. While conventional super-resolution aims to increase the spatial resolution of an input image, our goal is to spectrally enhance the input, i.e., generate an…
Hyperspectral images are crucial for many research works. Spectral super-resolution (SSR) is a method used to obtain high spatial resolution (HR) hyperspectral images from HR multispectral images. Traditional SSR methods include…
We introduce SPECTRE, a fully transformer-based foundation model for volumetric computed tomography (CT). Our Self-Supervised & Cross-Modal Pretraining for CT Representation Extraction (SPECTRE) approach utilizes scalable 3D Vision…
This paper presents a generative model method for multispectral image fusion in remote sensing which is trained without supervision. This method eases the supervision of learning and it also considers a multi-objective loss function to…
Implicit neural representations (INRs) have demonstrated success in a variety of applications, including inverse problems and neural rendering. An INR is typically trained to capture one signal of interest, resulting in learned neural…
Tactile representation learning (TRL) equips robots with the ability to leverage touch information, boosting performance in tasks such as environment perception and object manipulation. However, the heterogeneity of tactile sensors results…
Automatic speech recognition (ASR) and speech translation (ST) can both use neural transducers as the model structure. It is thus possible to use a single transducer model to perform both tasks. In real-world applications, such joint ASR…
Scanning Electron Microscopy (SEM) is indispensable in modern materials science, enabling high-resolution imaging across a wide range of structural, chemical, and functional investigations. However, SEM imaging remains constrained by…
Coded Aperture Snapshot Spectral Imaging (CASSI) reconstruction aims to recover the 3D spatial-spectral signal from 2D measurement. Existing methods for reconstructing Hyperspectral Image (HSI) typically involve learning mappings from a 2D…
Synthetic aperture radar (SAR) is a tomographic sensor that measures 2D slices of the 3D spatial Fourier transform of the scene. In many operational scenarios, the measured set of 2D slices does not fill the 3D space in the Fourier domain,…
We introduce the Spectroscopy Pre-trained Transformer (SpecPT), a transformer-based model designed to analyze spectroscopic data, with applications in spectrum reconstruction and redshift measurement. Using the Early Data Release (EDR) of…
Traditional radio map estimation (RME) techniques fail to capture multi-dimensional and dynamic characteristics of complex spectrum environments. Recent data-driven methods achieve accurate RME in spatial domain, but ignore physical prior…
Most existing CNN-based super-resolution (SR) methods are developed based on an assumption that the degradation is fixed and known (e.g., bicubic downsampling). However, these methods suffer a severe performance drop when the real…
We present Universal Sparse Autoencoders (USAEs), a framework for uncovering and aligning interpretable concepts spanning multiple pretrained deep neural networks. Unlike existing concept-based interpretability methods, which focus on a…
Astrophysical explorations are underpinned by large-scale stellar spectroscopy surveys, necessitating a paradigm shift in spectral fitting techniques. Our study proposes three enhancements to transcend the limitations of the current…
Remote Sensing (RS) is a crucial technology for observing, monitoring, and interpreting our planet, with broad applications across geoscience, economics, humanitarian fields, etc. While artificial intelligence (AI), particularly deep…
This paper proposes a universal sound separation (USS) method capable of handling untrained sampling frequencies (SFs). The USS aims at separating arbitrary sources of different types and can be the key technique to realize a source…
Real time sensor based applications in pervasive computing require edge deployable models to ensure low latency privacy and efficient interaction. A prime example is sensor based human activity recognition where models must balance accuracy…
Undirected graphical models have been successfully used to jointly model the spatial and the spectral dependencies in earth observing hyperspectral images. They produce less noisy, smooth, and spatially coherent land cover maps and give top…