Combi-CAM: A Novel Multi-Layer Approach for Explainable Image Geolocalization
This addresses the challenge of explainability in image geolocalization for researchers and practitioners, though it is incremental as it builds on existing CAM methods.
The paper tackles the problem of understanding CNN-based geolocalization predictions by introducing Combi-CAM, a method that combines gradient-weighted class activation maps from multiple network layers, resulting in more detailed explanations than traditional single-layer approaches.
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.