Related papers: Generalization from Low- to Moderate-Resolution Sp…

Magnetic Resonance Spectroscopy (MRS) is a noninvasive tool to reveal metabolic information. One challenge of 1H-MRS is the low Signal-Noise Ratio (SNR). To improve the SNR, a typical approach is to perform Signal Averaging (SA) with M…

Laser-induced breakdown spectroscopy (LIBS) is a popular, fast elemental analysis technique used to determine the chemical composition of target samples, such as in industrial analysis of metals or in space exploration. Recently, there has…

Parameter fine tuning is a transfer learning approach whereby learned parameters from pre-trained source network are transferred to the target network followed by fine-tuning. Prior research has shown that this approach is capable of…

A pretrain-finetune strategy is widely used to reduce the overfitting that can occur when data is insufficient for CNN training. First few layers of a CNN pretrained on a large-scale RGB dataset are capable of acquiring general image…

Deep Metric Learning (DML) is arguably one of the most influential lines of research for learning visual similarities with many proposed approaches every year. Although the field benefits from the rapid progress, the divergence in training…

Reinforcement learning (RL) is a key post-pretraining step for aligning large language models (LLMs) with complex tasks and human preferences. While it is often assumed that RL fine-tuning requires updating most of a model's parameters, we…

Spectral clustering is a leading and popular technique in unsupervised data analysis. Two of its major limitations are scalability and generalization of the spectral embedding (i.e., out-of-sample-extension). In this paper we introduce a…

Remote sensing images are essential for many applications of the earth's sciences, but their quality can usually be degraded due to limitations in sensor technology and complex imaging environments. To address this, various remote sensing…

The main focus of this work is a novel framework for the joint reconstruction and segmentation of parallel MRI (PMRI) brain data. We introduce an image domain deep network for calibrationless recovery of undersampled PMRI data. The proposed…

Prior research shows that large language models (LLMs) exhibit systematic extrapolation bias when forming predictions from both experimental and real-world data, and that prompt-based approaches appear limited in alleviating this bias. We…

This work studies deep metric learning under small to medium scale data as we believe that better generalization could be a contributing factor to the improvement of previous fine-grained image retrieval methods; it should be considered…

Although the sparse multinomial logistic regression (SMLR) has provided a useful tool for sparse classification, it suffers from inefficacy in dealing with high dimensional features and manually set initial regressor values. This has…

Deep neural networks trained as image denoisers are widely used as priors for solving imaging inverse problems. While Gaussian denoising is thought sufficient for learning image priors, we show that priors from deep models pre-trained as…

The pretrain-finetune paradigm is a classical pipeline in visual learning. Recent progress on unsupervised pretraining methods shows superior transfer performance to their supervised counterparts. This paper revisits this phenomenon and…

Conventional supervised super-resolution (SR) approaches are trained with massive external SR datasets but fail to exploit desirable properties of the given test image. On the other hand, self-supervised SR approaches utilize the internal…

Magnetic Resonance Imaging (MRI) is a widely used medical imaging technique, but its long acquisition time can be a limiting factor in clinical settings. To address this issue, researchers have been exploring ways to reduce the acquisition…

High resolution Magnetic Resonance (MR) images are desired for accurate diagnostics. In practice, image resolution is restricted by factors like hardware and processing constraints. Recently, deep learning methods have been shown to produce…

Fast data acquisition in Magnetic Resonance Imaging (MRI) is vastly in demand and scan time directly depends on the number of acquired k-space samples. Recently, the deep learning-based MRI reconstruction techniques were suggested to…

The fusion of hyperspectral image (HSI) with multispectral image (MSI) provides an effective way to enhance the spatial resolution of HSI. However, due to different acquisition conditions, there may exist spectral variability and spatially…

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…