AB
Publications
- Toward Scalable and Unified Example-Based Explanation and Outlier Detection
- Resolving challenges in deep learning-based analyses of histopathological images using explanation methods
- Beyond explaining: Opportunities and challenges of XAI-based model improvement
- Discovering Transferable Forensic Features for CNN-generated Images Detection
- To pretrain or not? A systematic analysis of the benefits of pretraining in diabetic retinopathy
- Towards best practice in explaining neural network decisions with LRP
- Exploring the Back Alleys: Analysing The Robustness of Alternative Neural Network Architectures against Adversarial Attacks
- Generalized PatternAttribution for Neural Networks with Sigmoid Activations
- BatchNorm Decomposition for Deep Neural Network Interpretation
- Simple and Effective Prevention of Mode Collapse in Deep One-Class Classification
- Towards Best Practice in Explaining Neural Network Decisions with LRP
- SmartOTPs: An Air-Gapped 2-Factor Authentication for Smart-Contract Wallets
- SideInfNet: A Deep Neural Network for Semi-Automatic Semantic Segmentation with Side Information
- Explanation-Guided Training for Cross-Domain Few-Shot Classification
- Deep Semi-Supervised Anomaly Detection
- Understanding Image Captioning Models beyond Visualizing Attention
- SideInfNet: A Deep Neural Network for Semi-Automatic Semantic Segmentation with Side Information
- Interpretable Deep Neural Network to Predict Estrogen Receptor Status from Haematoxylin-Eosin Images
- Simple and Effective Prevention of Mode Collapse in Deep One-Class Classification
- Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution
- Explain and improve: LRP-inference fine-tuning for image captioning models
- Morphological and molecular breast cancer profiling through explainable machine learning
- Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement
- Towards A Conceptually Simple Defensive Approach for Few-shot classifiers against Adversarial Support Samples
- On the robustness of pretraining and self-supervision for a deep learning-based analysis of diabetic retinopathy
- Detection of Adversarial Supports in Few-Shot Classifiers Using Self-Similarity and Filtering
- Detection of adversarial supports in few-shot classifiers using self-similarity and filtering
- Split and Expand: An inference-time improvement for Weakly Supervised Cell Instance Segmentation
- Explanation-guided training for Cross-domain few-shot classification
- Understanding integrated gradients with SmoothTaylor for deep neural network attribution
- SideInfNet: A deep neural network for semi-automatic semantic segmentation with side information
- Simple and effective prevention of mode collapse in deep one-class classification
- Explain and improve: LRP-inference fine-tuning for image captioning models
- DEEP SEMI-SUPERVISED ANOMALY DETECTION
- Exploring the back alleys: Analysing the robustness of alternative neural network architectures against adversarial attacks
- Deep semi-supervised anomaly detection
- Adversarial Attacks on Remote User Authentication Using Behavioural Mouse Dynamics
- To pretrain or not? A systematic analysis of the benefits of pretraining in diabetic retinopathy
- Toward Scalable and Unified Example-based Explanation and Outlier Detection
- OPTIMIZING EXPLANATIONS BY NETWORK CANONIZATION AND HYPERPARAMETER SEARCH
- Explanation-guided training for cross-domain few-shot classification
- Analysing the Adversarial Landscape of Binary Stochastic Networks
- Discovering Transferable Forensic Features for CNN-generated Images Detection
- Discovering Transferable Forensic Features for CNN-Generated Images Detection
- Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations
- Pruning by explaining: A novel criterion for deep neural network pruning
- Adaptive noise injection for training stochastic student networks from deterministic teachers
- Understanding integrated gradients with smoothtaylor for deep neural network attribution
- User Authentication Based on Mouse Dynamics Using Deep Neural Networks: A Comprehensive Study
- Adversarial Attacks on Remote User Authentication Using Behavioural Mouse Dynamics
- Evaluating the Visualization of What a Deep Neural Network Has Learned
- Learning and evaluation in presence of Non-i.i.d. label noise
- ImageCLEF 2017: ImageCLEF tuberculosis task - The SGEast submission
- The LRP toolbox for artificial neural networks
- Multi-class SVMs: From tighter data-dependent generalization bounds to novel algorithms
- Towards computational fluorescence microscopy: Machine learning-based integrated prediction of morphological and molecular tumor profiles
- Relevance score assignment for artificial neural networks
- Method and System for the Automatic Analysis of an Image of a Biological Sample
- Localized multiple kernel learning—a convex approach
- An Air-Gapped 2-Factor Authentication for Smart-Contract Wallets
- Deep Taylor Decomposition of Neural Networks
- Scoring of tumor-infiltrating lymphocytes: From visual estimation to machine learning
- Theory and Algorithms for the Localized Setting of Learning Kernels
- Analyzing and Validating Neural Networks Predictions
- Localized multiple kernel learning|A convex approach
- Mouse authentication without the temporal aspect - What does a 2D-CNN learn?
- DeepClue: Visual Interpretation of Text-based Deep Stock Prediction
- Thermal comfort based performance appraisal of covered walkways in Singapore
- Bag of Machine Learning Concepts for Visual Concept Recognition in Images
- Unmasking Clever Hans predictors and assessing what machines really learn
- Deep one-class classification
- Urban Zoning Using Higher-Order Markov Random Fields on Multi-View Imagery Data
- Pruning by explaining: A novel criterion for deep neural network pruning
- Towards best practice in explaining neural network decisions with LRP
- Resolving challenges in deep learning-based analyses of histopathological images using explanation methods
- Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
- SmartOTPs: An Air-Gapped 2-Factor Authentication for Smart-Contract Wallets
- Towards computational fluorescence microscopy: Machine learning-based integrated prediction of morphological and molecular tumor profiles
- Corplab Inli@FIRE-2018: Identification of indian native language using pairwise coupling
- Understanding and comparing deep neural networks for age and gender classification
- Layer-Wise Relevance Propagation: An Overview
- Detection of masqueraders based on graph partitioning of file system access events
- Memory snapshot dataset of a compromised host with malware using obfuscation evasion techniques
- On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
- Machine Learning for Visual Concept Recognition and Ranking for Images
- Identification of vehicle tracks and association to wireless endpoints by multiple sensor modalities
- Multiple Kernel Learning for Brain-Computer Interfacing
- Enhanced representation and multi-task learning for image annotation
- Multi-modal identification and tracking of vehicles in partially observed environments
- Layer-Wise Relevance Propagation for Deep Neural Network Architectures
- Extracting latent brain states — Towards true labels in cognitive neuroscience experiments
- When brain and behavior disagree: Tackling systematic label noise in EEG data with machine learning
- Comparison of deep learning architectures for H&E histopathology images
- Object Boundary Detection and Classification with Image-Level Labels
- Understanding and Comparing Deep Neural Networks for Age and Gender Classification
- Insights from curve fitting models in mouse dynamics authentication systems
- Controlling explanatory heatmap resolution and semantics via decomposition depth
- Analyzing Classifiers: Fisher Vectors and Deep Neural Networks
- Layer-Wise Relevance Propagation for Neural Networks with Local Renormalization Layers
- Explaining nonlinear classification decisions with deep Taylor decomposition
- Efficient Classification of Images with Taxonomies
- Shrinking large visual vocabularies using multi-label agglomerative information bottleneck
- Enhancing Image Classification with Class-wise Clustered Vocabularies
- B 17 Maschinelles Lernen, Mustererkennung in der Bildverarbeitung
- Multi-task Learning via Non-sparse Multiple Kernel Learning
- Enhancing Recognition of Visual Concepts with Primitive Color Histograms via Non-sparse Multiple Kernel Learning
- A procedure of adaptive kernel combination with kernel-target alignment for object classification
- On Taxonomies for Multi-class Image Categorization
- Multi-modal visual concept classification of images via Markov random walk over tags
- A Hybrid Supervised-Unsupervised Vocabulary Generation Algorithm for Visual Concept Recognition
- Insights from Classifying Visual Concepts with Multiple Kernel Learning
- Clinical relevance of CD95 (Fas/Apo-1) on T cells of patients with B-cell chronic lymphocytic leukemia
- The Shogun machine learning toolbox
- The joint submission of the TU Berlin and Fraunhofer FIRST (TUBFI) to the image CLEF 2011 photo annotation task
- Fraunhofer FIRST's submission to ImageCLEF2009 photo annotation task: Non-sparse multiple kernel learning