23 citations · 38 across the 19 of their papers we have counts for
21 papers
Failure or Drift? Evaluating Monocular SLAM under Synthetic and Real-World Corruptions
Abhay Skaria Thomas, Shashank Agnihotri, Margret Keuper
Visual SLAM is commonly evaluated on clean trajectories, although deployment failures are often caused by adverse weather, illumination, blur, and sensor artifacts. Controlled corr…
Images as Tables: In-Context Learning with TabPFN for Low-Data Detection of AI-Generated Images
Jan Philip Walter, Shashank Agnihotri, Margret Keuper
AI-generated image detection is a moving-target problem: detectors trained on one generator often fail when a new generator appears, and only a few labeled examples are available.…
GeoDiv: Framework For Measuring Geographical Diversity In Text-To-Image Models
Abhipsa Basu, Mohana Singh, Shashank Agnihotri +2
Text-to-image (T2I) models are rapidly gaining popularity, yet their outputs often lack geographical diversity, reinforce stereotypes, and misrepresent regions. Given their broad r…
RAWDet-7: A Multi-Scenario Benchmark for Object Detection and Description on Quantized RAW Images
Mishal Fatima, Shashank Agnihotri, Kanchana Vaishnavi Gandikota +2
Most vision models are trained on RGB images processed through ISP pipelines optimized for human perception, which can discard sensor-level information useful for machine reasoning…
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…
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…
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…
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…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1168
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…
How Do Training Methods Influence the Utilization of Vision Models?
Paul Gavrikov, Shashank Agnihotri, Margret Keuper +1
Not all learnable parameters (e.g., weights) contribute equally to a neural network's decision function. In fact, entire layers' parameters can sometimes be reset to random values…
Beware of Aliases -- Signal Preservation is Crucial for Robust Image Restoration
Shashank Agnihotri, Julia Grabinski, Janis Keuper +1
Image restoration networks are usually comprised of an encoder and a decoder, responsible for aggregating image content from noisy, distorted data and to restore clean, undistorted…
Improving Feature Stability during Upsampling -- Spectral Artifacts and the Importance of Spatial Context
Shashank Agnihotri, Julia Grabinski, Margret Keuper
Pixel-wise predictions are required in a wide variety of tasks such as image restoration, image segmentation, or disparity estimation. Common models involve several stages of data…
On the unreasonable vulnerability of transformers for image restoration -- and an easy fix
Shashank Agnihotri, Kanchana Vaishnavi Gandikota, Julia Grabinski +2
Following their success in visual recognition tasks, Vision Transformers(ViTs) are being increasingly employed for image restoration. As a few recent works claim that ViTs for imag…
Differentiable Sensor Layouts for End-to-End Learning of Task-Specific Camera Parameters
Hendrik Sommerhoff, Shashank Agnihotri, Mohamed Saleh +3
The success of deep learning is frequently described as the ability to train all parameters of a network on a specific application in an end-to-end fashion. Yet, several design cho…
CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks
Shashank Agnihotri, Steffen Jung, Margret Keuper
While neural networks allow highly accurate predictions in many tasks, their lack of robustness towards even slight input perturbations often hampers their deployment. Adversarial…