相关论文: Inferring Height from Earth Embeddings: First insi…

We study the image-based geolocalization problem, aiming to localize ground-view query images on cartographic maps. Current methods often utilize cross-view localization techniques to match ground-view query images with 2D maps. However,…

In this paper we address the challenge of land cover classification for satellite images via Deep Learning (DL). Land Cover aims to detect the physical characteristics of the territory and estimate the percentage of land occupied by a…

Understanding how explicit theoretical features are encoded in opaque neural systems is a central challenge now common to neuroscience and AI. We introduce Metric Learning Encoding Models (MLEMs) to address this challenge most directly as a…

Accurate estimation of building heights is essential for urban planning, infrastructure management, and environmental analysis. In this study, we propose a supervised Multimodal Building Height Regression Network (MBHR-Net) for estimating…

Understanding terrain topology at long-range is crucial for the success of off-road robotic missions, especially when navigating at high-speeds. LiDAR sensors, which are currently heavily relied upon for geometric mapping, provide sparse…

In this work, we develop methods for few-shot image classification from a new perspective of optimal matching between image regions. We employ the Earth Mover's Distance (EMD) as a metric to compute a structural distance between dense image…

Classification and identification of the materials lying over or beneath the Earth's surface have long been a fundamental but challenging research topic in geoscience and remote sensing (RS) and have garnered a growing concern owing to the…

Vision-Language Encoders (VLEs) are widely adopted as the backbone of zero-shot referring image segmentation (RIS), enabling text-guided localization without task-specific training. However, prior works underexplored the underlying biases…

Altered fingerprint recognition (AFR) is challenging for biometric verification in applications such as border control, forensics, and fiscal admission. Adversaries can deliberately modify ridge patterns to evade detection, so robust…

Modern DNN-based recommendation systems rely on training-derived embeddings of sparse features. Input sparsity makes obtaining high-quality embeddings for rarely-occurring categories harder as their representations are updated infrequently.…

Unifying the correlative single-view satellite image building extraction and height estimation tasks indicates a promising way to share representations and acquire generalist model for large-scale urban 3D reconstruction. However, the…

The rapid advancement of large language models (LLMs) has enabled significant strides in various fields. This paper introduces a novel approach to evaluate the effectiveness of LLM embeddings in the context of inherent geometric properties.…

Learning representations of geographical space is vital for any machine learning model that integrates geolocated data, spanning application domains such as remote sensing, ecology, or epidemiology. Recent work embeds coordinates using sine…

Existing deep embedding methods in vision tasks are capable of learning a compact Euclidean space from images, where Euclidean distances correspond to a similarity metric. To make learning more effective and efficient, hard sample mining is…

Deep convolutional networks (CNNs) have exhibited their potential in image inpainting for producing plausible results. However, in most existing methods, e.g., context encoder, the missing parts are predicted by propagating the surrounding…

Deep learning methods have played a more and more important role in hyperspectral image classification. However, the general deep learning methods mainly take advantage of the information of sample itself or the pairwise information between…

Earth observation (EO) missions produce petabytes of multispectral imagery, increasingly analyzed using large Geospatial Foundation Models (GeoFMs). Alongside end-to-end adaptation, workflows make growing use of intermediate representations…

Geometric properties of Transformer weights, particularly the unembedding matrix, have been widely useful in language model interpretability research. Yet, their utility for estimating downstream performance remains unclear. In this work,…

We explore the task of geometric reconstruction of images captured from a mixture of ground and aerial views. Current state-of-the-art learning-based approaches fail to handle the extreme viewpoint variation between aerial-ground image…

Deep neural networks can be effective means to automatically classify aerial images but is easy to overfit to the training data. It is critical for trained neural networks to be robust to variations that exist between training and test…