Publications

What could go wrong? Discovering and describing failure modes in computer vision

Gabriela Csurka, Tyler L. Hayes, Diane Larlus, Riccardo Volpi
Paper Poster

VTCD: Understanding Video Transformers via Universal Concept Discovery

Matthew Kowal, Achal Dave, Rares Andrei Ambrus, Adrien Gaidon, Konstantinos G. Derpanis, Pavel Tokmakov
Paper Poster Video

Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models

Matthew Kowal, Richard Wildes, Konstantinos G. Derpanis
Paper Poster Video

Top-GAP: Integrating Size Priors in CNNs for more Interpretability, Robustness, and Bias Mitigation

Lars Nieradzik, Henrike Stephani, Janis Keuper
Paper Poster

Q-SENN: Quantized Self-Explaining Neural Networks

Thomas Norrenbrock, Marco Rudolph, Bodo Rosenhahn
Paper

Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers

Sayed Mohammad Vakilzadeh Hatefi, Maximilian Dreyer, Reduan Achtibat, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
Paper Poster

ProactiV: Studying Deep Learning Model Behavior under Input Transformations

Vidya Prasad, Ruud Van Sloun, Anna Bartrolí, Nicola Pezzotti
Paper

PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers

Ananthu Aniraj, Cassio Fraga Dantas, Dino Ienco, Diego Marcos
Paper Poster Video

Network Inversion of Binarised Neural Nets

Pirzada Suhail
Paper

Localization-Guided Supervision for Robust Medical Image Classification by Vision Transformers

Sagi Ben Itzhak, Nahum Kiryati, Orith Portnoy, Arnaldo Mayer
Paper Poster

Interpretability benchmark for evaluating spatial misalignment of prototypical parts explanations

Mikołaj Sacha, Bartosz Jura, Dawid Damian Rymarczyk, Łukasz Struski, Jacek Tabor, Bartosz Michał Zieliński
Paper Poster

Integrating Local and Global Interpretability for Deep Concept-Based Reasoning Models

David Debot, Giuseppe Marra
Paper Poster

Image-guided topic modeling for interpretable privacy classification

Alina Elena Baia, Andrea Cavallaro
Paper Poster

Global Counterfactual Directions

Bartlomiej Sobieski, Przemyslaw Biecek
Paper Poster Video

From Flexibility to Manipulation: The Slippery Slope of XAI Evaluation

Kristoffer Wickstrøm, Marina MC Höhne, Anna Hedström
Paper Poster

Feature Contribution in Monocular Depth Estimation

Hui Yu Lau, Srinandan Dasmahapatra, Hansung Kim
Paper Poster

Explanation Alignment: Quantifying the Correctness of Model Reasoning At Scale

Hyemin Bang, Angie Boggust, Arvind Satyanarayan
Paper Poster

Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?

Jae Hee Lee, Georgii Mikriukov, Gesina Schwalbe, Stefan Wermter, Diedrich Wolter
Paper Poster

Can Biases in ImageNet Models Explain Generalization?

Paul Gavrikov, Janis Keuper
Paper

Attribute Based Interpretable Evaluation Metrics for Generative Models

Dongkyun Kim, Mingi Kwon, Youngjung Uh
Paper

As large as it gets: Learning infinitely large Filters via Neural Implicit Functions in the Fourier Domain

Julia Grabinski, Janis Keuper, Margret Keuper
Paper

Analyzing Vision Transformers for Image Classification in Class Embedding Space

Martina G. Vilas, Timothy Schaumlöffel, Gemma Roig
Paper

An Investigation on The Position Encoding in Vision-Based Dynamics Prediction

Jiageng Zhu, Hanchen Xie, Mahyar Khayatkhoei, Jiazhi Li, Wael AbdAlmageed
Paper Poster Video

"Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interaction

Sunnie S. Y. Kim, Elizabeth Anne Watkins, Olga Russakovsky, Ruth Fong, Andrés Monroy-Hernández
Paper