Cover Image

AIM: Amending Inherent Interpretability via Self-Supervised Masking

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Alshami, Eyad, Agnihotri, Shashank, Schiele, Bernt, Keuper, Margret
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Faithful, Interpretable Chest X-ray Diagnosis with Anti-Aliased B-cos Networks
by: Kleinmann, Marcel, et al.
Published: (2025)

CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks
by: Agnihotri, Shashank, et al.
Published: (2023)

Improving Feature Stability during Upsampling -- Spectral Artifacts and the Importance of Spatial Context
by: Agnihotri, Shashank, et al.
Published: (2023)

Smart Eyes for Silent Threats: VLMs and In-Context Learning for THz Imaging
by: Poggi, Nicolas, et al.
Published: (2025)

Images as Tables: In-Context Learning with TabPFN for Low-Data Detection of AI-Generated Images
by: Walter, Jan Philip, et al.
Published: (2026)

How Do Training Methods Influence the Utilization of Vision Models?
by: Gavrikov, Paul, et al.
Published: (2024)

Beware of Aliases -- Signal Preservation is Crucial for Robust Image Restoration
by: Agnihotri, Shashank, et al.
Published: (2024)

B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers
by: Böhle, Moritz, et al.
Published: (2023)

Vision At Night: Exploring Biologically Inspired Preprocessing For Improved Robustness Via Color And Contrast Transformations
by: Stracke, Lorena, et al.
Published: (2025)

Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?
by: Agnihotri, Shashank, et al.
Published: (2025)

RAWDet-7: A Multi-Scenario Benchmark for Object Detection and Description on Quantized RAW Images
by: Fatima, Mishal, et al.
Published: (2026)

GeoDiv: Framework For Measuring Geographical Diversity In Text-To-Image Models
by: Basu, Abhipsa, et al.
Published: (2026)

B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable
by: Arya, Shreyash, et al.
Published: (2024)

DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions
by: Agnihotri, Shashank, et al.
Published: (2025)

Deepfakes: we need to re-think the concept of "real" images
by: Keuper, Janis, et al.
Published: (2025)

As large as it gets: Learning infinitely large Filters via Neural Implicit Functions in the Fourier Domain
by: Grabinski, Julia, et al.
Published: (2023)

MTA-CLIP: Language-Guided Semantic Segmentation with Mask-Text Alignment
by: Das, Anurag, et al.
Published: (2024)

$γ$-Quant: Towards Learnable Quantization for Low-bit Pattern Recognition
by: Fatima, Mishal, et al.
Published: (2025)

Optimising for Interpretability: Convolutional Dynamic Alignment Networks
by: Böhle, Moritz, et al.
Published: (2021)

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs
by: Kuzucu, Selim, et al.
Published: (2025)

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models
by: Xie, Jiahao, et al.
Published: (2026)

OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning
by: Ahmed, Noor, et al.
Published: (2024)

RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo
by: Oei, Victor, et al.
Published: (2025)

Interpretable 3D Neural Object Volumes for Robust Conceptual Reasoning
by: Pham, Nhi, et al.
Published: (2025)

SemSegBench & DetecBench: Benchmarking Reliability and Generalization Beyond Classification
by: Agnihotri, Shashank, et al.
Published: (2025)

Unfolding Local Growth Rate Estimates for (Almost) Perfect Adversarial Detection
by: Lorenz, Peter, et al.
Published: (2022)

Scribbles for All: Benchmarking Scribble Supervised Segmentation Across Datasets
by: Boettcher, Wolfgang, et al.
Published: (2024)

Do Instance Priors Help Weakly Supervised Semantic Segmentation?
by: Das, Anurag, et al.
Published: (2026)

SimNP: Learning Self-Similarity Priors Between Neural Points
by: Wewer, Christopher, et al.
Published: (2023)

VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow
by: Gorgun, Ada, et al.
Published: (2025)

DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring
by: Dong, Jiangxin, et al.
Published: (2021)

Rewis3d: Reconstruction Improves Weakly-Supervised Semantic Segmentation
by: Ernst, Jonas, et al.
Published: (2026)

Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling
by: Grabinski, Julia, et al.
Published: (2023)

Know Yourself Better: Diverse Object-Related Features Improve Open Set Recognition
by: Xu, Jiawen, et al.
Published: (2024)

TRIX- Trading Adversarial Fairness via Mixed Adversarial Training
by: Medi, Tejaswini, et al.
Published: (2025)

Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models
by: Müller, Patrick, et al.
Published: (2025)

Corner Cases: How Size and Position of Objects Challenge ImageNet-Trained Models
by: Fatima, Mishal, et al.
Published: (2025)

Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?
by: Lorenz, Peter, et al.
Published: (2021)

Informed Mixing -- Improving Open Set Recognition via Attribution-based Augmentation
by: Xu, Jiawen, et al.
Published: (2025)

Better Understanding Differences in Attribution Methods via Systematic Evaluations
by: Rao, Sukrut, et al.
Published: (2023)