Combi-CAM: A Novel Multi-Layer Approach for Explainable Image Geolocalization

2026-03-25

AI Summary

This work addresses the limited interpretability of existing vision-based image geolocation models, which often fail to reveal the rationale behind their predictions. To overcome this limitation, the authors propose a multi-layer gradient-weighted class activation mapping (Grad-CAM) fusion strategy that moves beyond conventional approaches relying solely on the deepest convolutional features. By integrating activation signals from both intermediate and deep layers of a convolutional neural network, the method generates finer-grained and more comprehensive visual explanations of model decisions. This approach substantially enhances model transparency and trustworthiness, outperforming existing single-layer Grad-CAM techniques in interpretability and providing richer, more accurate justifications for geolocation predictions.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Planet-scale photo geolocalization involves the intricate task of estimating the geographic location depicted in an image purely based on its visual features. While deep learning models, particularly convolutional neural networks (CNNs), have significantly advanced this field, understanding the reasoning behind their predictions remains challenging. In this paper, we present Combi-CAM, a novel method that enhances the explainability of CNN-based geolocalization models by combining gradient-weighted class activation maps obtained from several layers of the network architecture, rather than using only information from the deepest layer as is typically done. This approach provides a more detailed understanding of how different image features contribute to the model's decisions, offering deeper insights than the traditional approaches.

Problem

• image geolocalization
• explainability
• deep learning
• convolutional neural networks
• model interpretability

Innovation

• Combi-CAM
• explainable AI
• image geolocalization
• multi-layer activation maps
• CNN interpretability