176 citations · 250 across the 54 of their papers we have counts for
15 papers · 1 filter
A Granular Study of Safety Pretraining under Model Abliteration
Shashank Agnihotri, Jonas Jakubassa, Priyam Dey +4
Open-weight LLMs can be modified at inference time with simple activation edits, which raises a practical question for safety: do common safety interventions like refusal training…
-Quant: Towards Learnable Quantization for Low-bit Pattern Recognition
Mishal Fatima, Shashank Agnihotri, Marius Bock +4
Most pattern recognition models are developed on pre-proce\-ssed data. In computer vision, for instance, RGB images processed through image signal processing (ISP) pipelines design…
Improved Robustness from Biologically Inspired Sparse Contrast Representations
Lorena Stracke, Lia Nimmermann, Shashank Agnihotri +3
Deep neural networks surpass humans on many vision benchmarks, yet remain far less robust to distribution shifts such as illumination and weather changes. Existing approaches addre…
Deepfakes: we need to re-think the concept of "real" images
Janis Keuper, Margret Keuper
The wide availability and low usability barrier of modern image generation models has triggered the reasonable fear of criminal misconduct and negative social implications. The mac…
AIM: Amending Inherent Interpretability via Self-Supervised Masking
Eyad Alshami, Shashank Agnihotri, Bernt Schiele +1
It has been observed that deep neural networks (DNNs) often use both genuine as well as spurious features. In this work, we propose "Amending Inherent Interpretability via Self-Sup…
Faithful, Interpretable Chest X-ray Diagnosis with Artifact-free B-cos Networks
Shreyash Arya, Marcel Kleinmann, Shashank Agnihotri +2
Faithfulness and interpretability are essential for deploying deep neural networks (DNNs) in safety-critical domains such as medical image analysis. B-cos networks modify the param…
Smart Eyes for Silent Threats: VLMs and In-Context Learning for THz Imaging
Nicolas Poggi, Shashank Agnihotri, Margret Keuper
Terahertz (THz) imaging enables non-invasive analysis for applications such as security screening and material classification, but effective image classification remains challengin…
TRIX- Trading Adversarial Fairness via Mixed Adversarial Training
Tejaswini Medi, Steffen Jung, Margret Keuper
Adversarial Training (AT) is a widely adopted defense against adversarial examples. However, existing approaches typically apply a uniform training objective across all classes, ov…
SemSegBench & DetecBench: Benchmarking Reliability and Generalization Beyond Classification
Shashank Agnihotri, David Schader, Jonas Jakubassa +5
Reliability and generalization in deep learning are predominantly studied in the context of image classification. Yet, real-world applications in safety-critical domains involve a…
Informed Mixing -- Improving Open Set Recognition via Attribution-based Augmentation
Jiawen Xu, Odej Kao, Margret Keuper
Open set recognition (OSR) is devised to address the problem of detecting novel classes during model inference. Even in recent vision models, this remains an open issue which is re…
DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions
Shashank Agnihotri, Amaan Ansari, Annika Dackermann +2
Deep learning (DL) has surpassed human performance on standard benchmarks, driving its widespread adoption in computer vision tasks. One such task is disparity estimation, estimati…
Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?
Shashank Agnihotri, David Schader, Nico Sharei +2
Deep learning (DL) models are widely used in real-world applications but remain vulnerable to distribution shifts, especially due to weather and lighting changes. Collecting divers…
RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo
Victor Oei, Jenny Schmalfuss, Lukas Mehl +5
Standard benchmarks for optical flow, scene flow, and stereo vision algorithms generally focus on model accuracy rather than robustness to image corruptions like noise or rain. Hen…
Corner Cases: How Size and Position of Objects Challenge ImageNet-Trained Models
Mishal Fatima, Steffen Jung, Margret Keuper
Backgrounds in images play a major role in contributing to spurious correlations among different data points. Owing to aesthetic preferences of humans capturing the images, dataset…
Deep Learning for Climate Action: Computer Vision Analysis of Visual Narratives on X
Katharina Prasse, Marcel Kleinmann, Inken Adam +8
Climate change is one of the most pressing challenges of the 21st century, sparking widespread discourse across social media platforms. Activists, policymakers, and researchers see…