5 papers
ResLRP: The Role of Residual Cancellation in Attribution Instability in Vision Transformers
Jim Berend, Reduan Achtibat, Daniel Schäffer +4
Vision Transformers (ViTs) are central to most modern vision models, yet obtaining input attributions that are fine-grained, faithful, and stable remains challenging. Layer-wise Re…
Beyond Spatial Compression: Interface-Centric Generative States for Open-World 3D Structure
Xiang Chen, Alexander Binder
Current 3D tokenizers largely treat representation as spatial compression: compact codes reconstruct surface geometry, but leave component ownership and attachment validity implici…
Value bounds and Convergence Analysis for Averages of LRP attributions
Alexander Binder, Nastaran Takmil-Homayouni, Urun Dogan
We analyze numerical properties of Layer-wise relevance propagation (LRP)-type attribution methods by representing them as a product of modified gradient matrices. This representat…
Revisiting Model Inversion Evaluation: From Misleading Standards to Reliable Privacy Assessment
Sy-Tuyen Ho, Koh Jun Hao, Ngoc-Bao Nguyen +2
Model Inversion attacks aim to reconstruct information from private training data by exploiting access to a target model. Nearly all recent MI studies evaluate attack success using…
Are nuclear masks all you need for improved out-of-domain generalisation? A closer look at cancer classification in histopathology
Dhananjay Tomar, Alexander Binder, Andreas Kleppe
Domain generalisation in computational histopathology is challenging because the images are substantially affected by differences among hospitals due to factors like fixation and s…