Related papers: Multi-modal, multi-scale representation learning f…
Sparse observations and coarse-resolution climate models limit effective regional decision-making, underscoring the need for robust downscaling. However, existing AI methods struggle with generalization across variables and geographies and…
Most of the existing Zero-Shot Learning (ZSL) methods focus on learning a compatibility function between the image representation and class attributes. Few others concentrate on learning image representation combining local and global…
High-resolution aerial images have a wide range of applications, such as military exploration, and urban planning. Semantic segmentation is a fundamental method extensively used in the analysis of high-resolution aerial images. However, the…
Transformers are very effective in capturing both global and local correlations within high-energy particle collisions, but they present deployment challenges in high-data-throughput environments, such as the CERN LHC. The quadratic…
For numerous earth observation applications, one may benefit from various satellite sensors to address the reconstruction of some process or information of interest. A variety of satellite sensors deliver observation data with different…
As a specific semantic segmentation task, aerial imagery segmentation has been widely employed in high spatial resolution (HSR) remote sensing images understanding. Besides common issues (e.g. large scale variation) faced by general…
Multimodal Transformers serve as the backbone for state-of-the-art vision-language models, yet their quadratic attention complexity remains a critical barrier to scalability. In this work, we investigate the viability of Linear Attention…
Self-supervised learning (SSL) has emerged as a powerful strategy for representation learning under limited annotation regimes, yet its effectiveness remains highly sensitive to many factors, especially the nature of the target task. In…
Salient object detection requires a comprehensive and scalable receptive field to locate the visually significant objects in the image. Recently, the emergence of visual transformers and multi-branch modules has significantly enhanced the…
Recent advances in imitation learning have shown significant promise for robotic control and embodied intelligence. However, achieving robust generalization across diverse mounted camera observations remains a critical challenge. In this…
LiDAR semantic segmentation models are typically trained from random initialization as universal pre-training is hindered by the lack of large, diverse datasets. Moreover, most point cloud segmentation architectures incorporate custom…
This paper proposes an attributable visual similarity learning (AVSL) framework for a more accurate and explainable similarity measure between images. Most existing similarity learning methods exacerbate the unexplainability by mapping each…
Rapid identification of damaged buildings after natural disasters or on war areas is crucial to support emergency response and prioritize interventions. Earth Observation constellations provide timely, large-scale coverage, but actionable…
Processing spatial data is a key component in many learning tasks for autonomous driving such as motion forecasting, multi-agent simulation, and planning. Prior works have demonstrated the value in using SE(2) invariant network…
In today's ever-connected world, the demand for fast and widespread connectivity is insatiable, making multibeam satellite systems an indispensable pillar of modern telecommunications infrastructure. However, the evolving communication…
Satellites continuously generate massive volumes of data, particularly for Earth observation, including satellite image time series (SITS). However, most deep learning models are designed to process either entire images or complete time…
Camera calibration consists of estimating camera parameters such as the zenith vanishing point and horizon line. Estimating the camera parameters allows other tasks like 3D rendering, artificial reality effects, and object insertion in an…
LibBi is a software package for state-space modelling and Bayesian inference on modern computer hardware, including multi-core central processing units (CPUs), many-core graphics processing units (GPUs) and distributed-memory clusters of…
Machine learning offers promising methods for processing signals recorded with wearable devices such as surface electromyography (sEMG) and electroencephalography (EEG). However, in these applications, despite high within-session…
Aerial-to-ground image synthesis is an emerging and challenging problem that aims to synthesize a ground image from an aerial image. Due to the highly different layout and object representation between the aerial and ground images, existing…