Investigating Different Geo Priors for Image Classification

• URL: http://arxiv.org/abs/2508.15946v1
• Date: Thu, 21 Aug 2025 20:28:35 GMT
• Title: Investigating Different Geo Priors for Image Classification
• Authors: Angela Zhu, Christian Lange, Max Hamilton,
• Abstract summary: Species distribution models encode spatial patterns of species occurrence making them effective priors for vision-based species classification.<n>We evaluate various SINR (Spatial Implicit Neural Representations) models as a geographical prior for visual classification of species from iNaturalist observations.
• Score: 3.8021161037738835
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Species distribution models encode spatial patterns of species occurrence making them effective priors for vision-based species classification when location information is available. In this study, we evaluate various SINR (Spatial Implicit Neural Representations) models as a geographical prior for visual classification of species from iNaturalist observations. We explore the impact of different model configurations and adjust how we handle predictions for species not included in Geo Prior training. Our analysis reveals factors that contribute to the effectiveness of these models as Geo Priors, factors that may differ from making accurate range maps.

Related papers

• Heterogeneous graph neural networks for species distribution modeling [6.423278804632857]
  We introduce a novel presence-only Species Distribution Model (SDM) with graph neural networks (GNN)<n>In our model, species and locations are treated as two distinct node sets, and the learning task is predicting detection records as the edges that connect locations to species.<n>We evaluate the potential of this methodology on the six-region dataset compiled by National Center for Ecological Analysis and Synthesis (NCEAS) for benchmarking SDMs.
  arXiv  Detail & Related papers  (2025-03-14T22:08:30Z)
• Feedforward Few-shot Species Range Estimation [61.60698161072356]
  Knowing where a particular species can or cannot be found on Earth is crucial for ecological research and conservation efforts.<n> accurate range estimates are only available for a relatively small proportion of all known species.<n>We outline a new approach for few-shot species range estimation to address the challenge of accurately estimating the range of a species from limited data.
  arXiv  Detail & Related papers  (2025-02-20T19:13:29Z)
• Enhancing GeoAI and location encoding with spatial point pattern statistics: A Case Study of Terrain Feature Classification [2.724802833397066]
  This study introduces a novel approach to terrain feature classification incorporating spatial point pattern statistics into deep learning models. We improve the GeoAI model by a knowledge driven approach to integrate both first-order and second-order effects of point patterns.
  arXiv  Detail & Related papers  (2024-11-21T20:17:41Z)
• LD-SDM: Language-Driven Hierarchical Species Distribution Modeling [9.620416509546471]
  We focus on the problem of species distribution modeling using global-scale presence-only data. To capture a stronger implicit relationship between species, we encode the taxonomic hierarchy of species using a large language model. We propose a novel proximity-aware evaluation metric that enables evaluating species distribution models.
  arXiv  Detail & Related papers  (2023-12-13T18:11:37Z)
• Spatial Implicit Neural Representations for Global-Scale Species Mapping [72.92028508757281]
  Given a set of locations where a species has been observed, the goal is to build a model to predict whether the species is present or absent at any location. Traditional methods struggle to take advantage of emerging large-scale crowdsourced datasets. We use Spatial Implicit Neural Representations (SINRs) to jointly estimate the geographical range of 47k species simultaneously.
  arXiv  Detail & Related papers  (2023-06-05T03:36:01Z)
• GeoNet: Benchmarking Unsupervised Adaptation across Geographies [71.23141626803287]
  We study the problem of geographic robustness and make three main contributions. First, we introduce a large-scale dataset GeoNet for geographic adaptation. Second, we hypothesize that the major source of domain shifts arise from significant variations in scene context. Third, we conduct an extensive evaluation of several state-of-the-art unsupervised domain adaptation algorithms and architectures.
  arXiv  Detail & Related papers  (2023-03-27T17:59:34Z)
• Spatial machine-learning model diagnostics: a model-agnostic distance-based approach [91.62936410696409]
  This contribution proposes spatial prediction error profiles (SPEPs) and spatial variable importance profiles (SVIPs) as novel model-agnostic assessment and interpretation tools. The SPEPs and SVIPs of geostatistical methods, linear models, random forest, and hybrid algorithms show striking differences and also relevant similarities. The novel diagnostic tools enrich the toolkit of spatial data science, and may improve ML model interpretation, selection, and design.
  arXiv  Detail & Related papers  (2021-11-13T01:50:36Z)
• Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders [72.15087604017441]
  Category-selectivity describes the observation that certain spatially localized areas of the cerebral cortex tend to respond robustly and selectively to stimuli from specific limited categories. We leverage the newly introduced Topographic Variational Autoencoder to model of the emergence of such localized category-selectivity in an unsupervised manner. We show preliminary results suggesting that our model yields a nested spatial hierarchy of increasingly abstract categories, analogous to observations from the human ventral temporal cortex.
  arXiv  Detail & Related papers  (2021-10-25T11:37:41Z)
• Selecting Treatment Effects Models for Domain Adaptation Using Causal Knowledge [82.5462771088607]
  We propose a novel model selection metric specifically designed for ITE methods under the unsupervised domain adaptation setting. In particular, we propose selecting models whose predictions of interventions' effects satisfy known causal structures in the target domain.
  arXiv  Detail & Related papers  (2021-02-11T21:03:14Z)
• Meta-Learning for Few-Shot Land Cover Classification [3.8529010979482123]
  We evaluate the model-agnostic meta-learning (MAML) algorithm on classification and segmentation tasks. We find that few-shot model adaptation outperforms pre-training with regular gradient descent. This indicates that model optimization with meta-learning may benefit tasks in the Earth sciences.
  arXiv  Detail & Related papers  (2020-04-28T09:42:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.