9 papers · 1 filter
Rank-based Geographical Regularization: Revisiting Contrastive Self-Supervised Learning for Multispectral Remote Sensing Imagery
Tom Burgert, Leonard Hackel, Paolo Rota +1
Self-supervised learning (SSL) has become a powerful paradigm for learning from large, unlabeled datasets, particularly in computer vision (CV). However, applying SSL to multispect…
How Much of a Model Do We Need? Redundancy and Slimmability in Remote Sensing Foundation Models
Leonard Hackel, Tom Burgert, Begüm Demir
Large-scale foundation models (FMs) in remote sensing (RS) (denoted as RS FMs) are developed following paradigms established in computer vision (CV), yet the validity of transferri…
Noise-Adaptive Regularization for Robust Multi-Label Remote Sensing Image Classification
Tom Burgert, Julia Henkel, Begüm Demir
The development of reliable methods for multi-label classification (MLC) has become a prominent research direction in remote sensing (RS). As the scale of RS data continues to expa…
ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression
Tom Burgert, Oliver Stoll, Paolo Rota +1
The hypothesis that Convolutional Neural Networks (CNNs) are inherently texture-biased has shaped much of the discourse on feature use in deep learning. We revisit this hypothesis…
CSMoE: An Efficient Remote Sensing Foundation Model with Soft Mixture-of-Experts
Leonard Hackel, Tom Burgert, Begüm Demir
Self-supervised learning (SSL) through masked autoencoders (MAEs) has recently attracted great attention for remote sensing (RS) foundation model (FM) development, enabling improve…
On the Effectiveness of Methods and Metrics for Explainable AI in Remote Sensing Image Scene Classification
Jonas Klotz, Tom Burgert, Begüm Demir
The development of explainable artificial intelligence (xAI) methods for scene classification problems has attracted great attention in remote sensing (RS). Most xAI methods and th…