9 papers
-Resilience: Model-Free Feature Importance from 1D Topological Signals
Fabian Galis, Darian Onchis, Pedro Real Jurado
We introduce -Resilience, a model-free feature importance method that derives explanations directly from the data itself via 1D topological signals. Our method constructs a clas…
ScoresActivation: A New Activation Function for Model Agnostic Global Explainability by Design
Emanuel Covaci, Fabian Galis, Radu Balan +2
Understanding the decision of large deep learning models is a critical challenge for building transparent and trustworthy systems. Although the current post hoc explanation methods…
Refining Filter Global Feature Weighting for Fully-Unsupervised Clustering
Fabian Galis, Darian Onchis
In the context of unsupervised learning, effective clustering plays a vital role in revealing patterns and insights from unlabeled data. However, the success of clustering algorith…
ExDDV: A New Dataset for Explainable Deepfake Detection in Video
Vlad Hondru, Eduard Hogea, Darian Onchis +1
The ever growing realism and quality of generated videos makes it increasingly harder for humans to spot deepfake content, who need to rely more and more on automatic deepfake dete…
ViTmiX: Vision Transformer Explainability Augmented by Mixed Visualization Methods
Eduard Hogea, Darian M. Onchis, Ana Coporan +2
Recent advancements in Vision Transformers (ViT) have demonstrated exceptional results in various visual recognition tasks, owing to their ability to capture long-range dependencie…
FeTrIL++: Feature Translation for Exemplar-Free Class-Incremental Learning with Hill-Climbing
Eduard Hogea, Adrian Popescu, Darian Onchis +1
Exemplar-free class-incremental learning (EFCIL) poses significant challenges, primarily due to catastrophic forgetting, necessitating a delicate balance between stability and plas…
Neuro-symbolic model for cantilever beams damage detection
Darian Onchis, Gilbert-Rainer Gillich, Eduard Hogea +1
In the last decade, damage detection approaches swiftly changed from advanced signal processing methods to machine learning and especially deep learning models, to accurately and n…
Dataset Knowledge Transfer for Class-Incremental Learning without Memory
Habib Slim, Eden Belouadah, Adrian Popescu +1
Incremental learning enables artificial agents to learn from sequential data. While important progress was made by exploiting deep neural networks, incremental learning remains ver…
An optimally concentrated Gabor transform for localized time-frequency components
Benjamin Ricaud, Guillaume Stempfel, Bruno Torrésani +3
Gabor analysis is one of the most common instances of time-frequency signal analysis. Choosing a suitable window for the Gabor transform of a signal is often a challenge for practi…