Tom Oswald Burgert
Tom Oswald Burgert
Doctoral Researcher
Leonard Hackel, Tom Burgert, Begüm Demir
How Much of a Model Do We Need? Redundancy and Slimmability in Remote Sensing Foundation Models
Tom Burgert, Julia Henkel, Begüm Demir
Noise-Adaptive Regularization for Robust Multi-Label Remote Sensing Image Classification
Tom Burgert, Leonard Hackel, Paolo Rota, Begüm Demir
Rank-based Geographical Regularization: Revisiting Contrastive Self-Supervised Learning for Multispectral Remote Sensing Imagery
Tom Burgert, Oliver Stoll, Paolo Rota, Begüm Demir
ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression
Leonard Hackel, Tom Burgert, Begüm Demir
CSMoE: An Efficient Remote Sensing Foundation Model with Soft Mixture-of-Experts
Rethinking how models "see"
Congratulations to BIFOLD researchers Tom Burgert, Oliver Stoll, and Begüm Demir from TU Berlin, and Paolo Rota from the University of Trento. They published a new study, that revisits a central claim in computer vision: so-called convolutional neural networks (CNNs) primarily rely on texture, rather than object shape, to recognize images. The publication was accepted as an oral presentation at NeurIPS 2025.