Publications

What Variables Affect Out-of-Distribution Generalization in Pretrained Models?

Md Yousuf Harun, Kyungbok Lee, Jhair Gallardo, Giri P Krishnan, Christopher Kanan
Paper Code

VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow

Ada Görgün, Bernt Schiele, Jonas Fischer
Paper Code

Vision language models fail to translate detailed visual features into words

Pooyan Rahmanzadehgervi, Logan Bolton, Mohammad Reza Taesiri, Anh Totti Nguyen
Paper Poster

Vision language models are blind

Pooyan Rahmanzadehgervi, Logan Bolton, Mohammad Reza Taesiri, Anh Totti Nguyen
Paper Poster

Very Short and Accurate Explanations by Design

Prisha Shroff, Hancheng Min, Rene Vidal
Paper Poster

Unmasking the functionality of early layers in VLMs

Max Hartman, Vidhata Jayaraman, Moulik Choraria, Akhil Bhimaraju, Lav R. Varshney
Paper Poster

Towards Safer and Understandable Driver Intention Prediction

Mukilan Karuppasamy, Shankar Gangisetty, Shyam Nandan Rai, Carlo Masone, C.V. Jawahar
Paper

Toward a Principled Theory of XAI via Spectral Analysis

Amir Mehrpanah, Matteo Gamba, Hossein Azizpour
Paper Poster Supplementary

The Myth of Robust Classes: How Shielding Skews Perceived Stability

Ananyapam De, Benjamin Säfken
Paper Poster

TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models

Pooyan Rahmanzadehgervi, Hung Nguyen, Rosanne Liu, Long Mai, Anh Totti Nguyen
Paper Poster

SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutions

Jessica Bader, Leander Girrbach, Stephan Alaniz, Zeynep Akata
Paper

Semantic Resonance Maps: Cross-Modal Oscillations for Explainable Vision-Language Model Interpretability

Nevasini Sasikumar
Paper

Rethinking Explainer Trust: A Position on the Inconsistencies of Visual Explanations in Weakly Supervised Segmentation

Ayush Somani, Dilip K. Prasad
Paper Poster

Patch-wise Retrieval: An Interpretable Instance-Level Image Matching

Wonseok Choi, Sohwi Lim, Nam Hyeon-Woo, Moon Ye-Bin, Dong-ju Jeong, Jinyoung Hwang, Tae-Hyun Oh
Paper Poster Supplementary Video

LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision

Mateusz Pach, Koryna Lewandowska, Jacek Tabor, Bartosz Michał Zieliński, Dawid Damian Rymarczyk
Paper Poster

LR0.FM: Low-Res Benchmark and Improving Robustness for Zero-Shot Classification in Foundation Models

Priyank Pathak, Shyam Marjit, Shruti Vyas, Yogesh S Rawat
Paper

Keep the Faith: Faithful Explanations in Convolutional Neural Networks for Case-Based Reasoning

Tom Nuno Wolf, Fabian Bongratz, Anne-Marie Rickmann, Sebastian Pölsterl, Christian Wachinger
Paper Poster Supplementary

Is CLIP ideal? No. Can we fix it? Yes!

Raphi Kang, Yue Song, Georgia Gkioxari, Pietro Perona
Paper

Interpretable Open-Vocabulary Referring Object Detection with Reverse Contrast Attention

Drandreb Earl O. Juanico, Rowel Atienza, Jeffrey Kenneth Go
Paper Poster Supplementary Video Code

Hallucinatory Image Tokens: A Training-free EAZY Approach on Detecting and Mitigating Object Hallucinations in LVLMs

Liwei Che, Tony Qingze Liu, Jing Jia, Weiyi Qin, Ruixiang Tang, Vladimir Pavlovic
Paper

Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations

Dahee Kwon, Sehyun Lee, Jaesik Choi
Paper Poster

Gradient-based Visual Explanation for Transformer-based CLIP

Chenyang Zhao, Kun Wang, Xingyu Zeng, Rui Zhao, Antoni B. Chan
Paper

GFR-CAM: Gram-Schmidt Feature Reduction for Hierarchical Class Activation Maps

Kaveh Safavigerdini, Bahram Yaghooti, Amir Erfan Zareei Shams Abadi, Kannappan Palaniappan
Paper Poster

Explaining Object Detection Through Difference Map

Shujun Xia, Chenyang ZHAO, Antoni B. Chan
Paper Poster

Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability

Ashwath Vaithinathan Aravindan, Abha Jha, Mihir Nitin Kulkarni
Paper Poster

DCBM: Data-Efficient Visual Concept Bottleneck Models

Katharina Prasse, Patrick Knab, Sascha Marton, Christian Bartelt, Margret Keuper
Paper Poster Video

Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning

Md Yousuf Harun, Jhair Gallardo, Christopher Kanan
Paper

CoCo-Bot: Energy-based Composable Concept Bottlenecks for Interpretable Generative Models

Sangwon Kim, In-su Jang, Pyongkun Kim, Kwang-Ju Kim
Paper Poster

Causal Interpretation of Sparse Autoencoder Features in Vision

Sangyu Han, Yearim Kim, Nojun Kwak
Paper Poster

BayesSDF: Surface-Based Laplacian Uncertainty Estimation for 3D Geometry with Neural Signed Distance Fields

Rushil Paresh Desai
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 Code

AIM: Amending Inherent Interpretability via Self-Supervised Masking

Eyad Alshami, Shashank Agnihotri, Bernt Schiele, Margret Keuper
Paper