Related papers: Mitigating representation bias caused by missing p…

The problem of image-base person identification/recognition is to provide an identity to the image of an individual based on learned models that describe his/her appearance. Most traditional person identification systems rely on learning a…

Images suffer from heavy spatial redundancy because pixels in neighboring regions are spatially correlated. Existing approaches strive to overcome this limitation by reducing less meaningful image regions. However, current leading methods…

Hyperspectral images provide much more information than conventional imaging techniques, allowing a precise identification of the materials in the observed scene, but because of the limited spatial resolution, the observations are usually…

This work explores capabilities of the pre-trained CLIP vision-language model to identify satellite images affected by clouds. Several approaches to using the model to perform cloud presence detection are proposed and evaluated, including a…

Hyperspectral images have far more spectral bands than ordinary multispectral images. Rich band information provides more favorable conditions for the tremendous applications. However, significant increase in the dimensionality of spectral…

Low-shot image classification is a fundamental task in computer vision, and the emergence of large-scale vision-language models such as CLIP has greatly advanced the forefront of research in this field. However, most existing CLIP-based…

In this work, we investigate sensing parameter estimation in the presence of clutter in perceptive mobile networks (PMNs) that integrate radar sensing into mobile communications. Performing clutter suppression before sensing parameter…

Envelope method was recently proposed as a method to reduce the dimension of responses in multivariate regressions. However, when there exists missing data, the envelope method using the complete case observations may lead to biased and…

Data augmentation has been pivotal in successfully training deep learning models on classification tasks over the past decade. An important subclass of data augmentation techniques - which includes both label smoothing and Mixup - involves…

Dataset bias is a critical challenge in machine learning since it often leads to a negative impact on a model due to the unintended decision rules captured by spurious correlations. Although existing works often handle this issue based on…

The basic framework of depth completion is to predict a pixel-wise dense depth map using very sparse input data. In this paper, we try to solve this problem in a more effective way, by reformulating the regression-based depth estimation…

This paper presents a Bayesian algorithm for linear spectral unmixing of hyperspectral images that accounts for anomalies present in the data. The model proposed assumes that the pixel reflectances are linear mixtures of unknown endmembers,…

Mid-InfraRed spectroscopy is a promising label-free technique that can offer insights into morphological and pathological alterations in biological tissues at the molecular level. Owing to the development of the Fourier Transform InfraRed…

Recently, a number of image-mixing-based augmentation techniques have been introduced to improve the generalization of deep neural networks. In these techniques, two or more randomly selected natural images are mixed together to generate an…

We show that correlations between the camera used to acquire an image and the class label of that image can be exploited by convolutional neural networks (CNN), resulting in a model that "cheats" at an image classification task by…

Learning segmentation from noisy labels is an important task for medical image analysis due to the difficulty in acquiring highquality annotations. Most existing methods neglect the pixel correlation and structural prior in segmentation,…

Anthropogenic methane (CH4) point sources drive near-term climate forcing, safety hazards, and system inefficiencies. Space-based imaging spectroscopy is emerging as a tool for identifying emissions globally, but existing approaches largely…

One of the challenges in hyperspectral data analysis is the presence of mixed pixels. Mixed pixels are the result of low spatial resolution of hyperspectral sensors. Spectral unmixing methods decompose a mixed pixel into a set of endmembers…

For object detection, it is possible to view the prediction of bounding boxes as a reverse diffusion process. Using a diffusion model, the random bounding boxes are iteratively refined in a denoising step, conditioned on the image. We…

Label-free model evaluation, or AutoEval, estimates model accuracy on unlabeled test sets, and is critical for understanding model behaviors in various unseen environments. In the absence of image labels, based on dataset representations,…