11 papers · 1 filter
Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples
Oussama Bouanani, Jim Berend, Wojciech Samek +2
Neuron labeling assigns textual descriptions to internal units of deep networks. Existing approaches typically rely on highly activating examples, often yielding broad or misleadin…
Concept-based explanations of Segmentation and Detection models in Natural Disaster Management
Samar Heydari, Jawher Said, Galip Ãmit Yolcu +7
Deep learning models for flood and wildfire segmentation and object detection enable precise, real-time disaster localization when deployed on embedded drone platforms. However, in…
Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP
Lorenz Hufe, Constantin Venhoff, Erblina Purelku +3
Typographic attacks exploit multi-modal systems by injecting text into images, leading to targeted misclassifications, malicious content generation and even Vision-Language Model j…
Deep Learning-based Multi Project InP Wafer Simulation for Unsupervised Surface Defect Detection
EmÃlio Dolgener Cantú, Rolf Klemens Wittmann, Oliver Abdeen +4
Quality management in semiconductor manufacturing often relies on template matching with known golden standards. For Indium-Phosphide (InP) multi-project wafer manufacturing, low p…
Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video
Sonia Joseph, Praneet Suresh, Lorenz Hufe +7
Robust tooling and publicly available pre-trained models have helped drive recent advances in mechanistic interpretability for language models. However, similar progress in vision…
Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence
Frederik Pahde, Maximilian Dreyer, Leander Weber +5
With a growing interest in understanding neural network prediction strategies, Concept Activation Vectors (CAVs) have emerged as a popular tool for modeling human-understandable co…