Tom Oswald Burgert
Tom Oswald Burgert
Doctoral Researcher
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
Jonas Klotz, Tom Burgert, Begüm Demir
On the Effectiveness of Methods and Metrics for Explainable AI in Remote Sensing Image Scene Classification
Kai Norman Clasen, Leonard Hackel, Tom Burgert, Gencer Sumbul, Begüm Demir, Volker Markl
reBEN: Refined BigEarthNet Dataset for Remote Sensing Image Analysis
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.