Related papers: Auxiliary-task learning for geographic data with a…

Sequential learning of tasks using gradient descent leads to an unremitting decline in the accuracy of tasks for which training data is no longer available, termed catastrophic forgetting. Generative models have been explored as a means to…

The idea of using machine learning (ML) methods to reconstruct the dynamics of a system is the topic of recent studies in the geosciences, in which the key output is a surrogate model meant to emulate the dynamical model. In order to treat…

This paper investigates the impact of self-supervised learning, specifically image rotations, on various class-incremental learning paradigms. Here, each image with a predefined rotation is considered as a new class for training. At…

This paper introduces a principled approach for the design of a scalable general reinforcement learning agent. This approach is based on a direct approximation of AIXI, a Bayesian optimality notion for general reinforcement learning agents.…

Spatial autocorrelation and spatial heterogeneity widely exist in spatial data, which make the traditional machine learning model perform badly. Spatial domain generalization is a spatial extension of domain generalization, which can…

This study develops a spatial additive mixed modeling (AMM) approach estimating spatial and non-spatial effects from large samples, such as millions of observations. Although fast AMM approaches are already well-established, they are…

Deep embedding learning becomes more attractive for discriminative feature learning, but many methods still require hard-class mining, which is computationally complex and performance-sensitive. To this end, we propose Adaptive Large Margin…

Recently, self-supervised learning (SSL) methods have been used in pre-training the segmentation models for 2D and 3D medical images. Most of these methods are based on reconstruction, contrastive learning and consistency regularization.…

Key challenges for the deployment of reinforcement learning (RL) agents in the real world are the discovery, representation and reuse of skills in the absence of a reward function. To this end, we propose a novel approach to learn a…

Spatiotemporal modeling of economic aggregates is increasingly relevant in regional science due to the presence of both spatial spillovers and temporal dynamics. Traditional temporal disaggregation methods, such as Chow-Lin, often ignore…

The choice of representation for geographic location significantly impacts the accuracy of models for a broad range of geospatial tasks, including fine-grained species classification, population density estimation, and biome classification.…

Self-supervised learning (SSL) is an efficient approach that addresses the issue of limited training data and annotation shortage. The key part in SSL is its proxy task that defines the supervisory signals and drives the learning toward…

Effective suppression of surface-related multiples is essential to prevent imaging artifacts and erroneous structural interpretations. While conventional approaches rely on accurate priors or subsurface model knowledge, and supervised…

We propose a few-shot learning method for spatial regression. Although Gaussian processes (GPs) have been successfully used for spatial regression, they require many observations in the target task to achieve a high predictive performance.…

Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR). To date, no empirical study has systematically examined the effectiveness of existing methods, nor investigated the…

Zero-shot learning (ZSL) aims to recognize objects from novel unseen classes without any training data. Recently, structure-transfer based methods are proposed to implement ZSL by transferring structural knowledge from the semantic…

Visual autoregressive (VAR) models have recently emerged as a promising alternative for image generation, offering stable training, non-iterative inference, and high-fidelity synthesis through next-scale prediction. This encourages the…

Multi-agent reinforcement learning (MARL) under partial observability has long been considered challenging, primarily due to the requirement for each agent to maintain a belief over all other agents' local histories -- a domain that…

Cross-Domain Detection (XDD) aims to train an object detector using labeled image from a source domain but have good performance in the target domain with only unlabeled images. Existing approaches achieve this either by aligning the…

This paper introduces SOAR: Spilling with Orthogonality-Amplified Residuals, a novel data indexing technique for approximate nearest neighbor (ANN) search. SOAR extends upon previous approaches to ANN search, such as spill trees, that…