Interpretable Tensor Fusion

no code implementations • 7 May 2024 • Saurabh Varshneya, Antoine Ledent, Philipp Liznerski, Andriy Balinskyy, Purvanshi Mehta, Waleed Mustafa, Marius Kloft

Conventional machine learning methods are predominantly designed to predict outcomes based on a single data type.

Reimagining Anomalies: What If Anomalies Were Normal?

no code implementations • 22 Feb 2024 • Philipp Liznerski, Saurabh Varshneya, Ece Calikus, Sophie Fellenz, Marius Kloft

Deep learning-based methods have achieved a breakthrough in image anomaly detection, but their complexity introduces a considerable challenge to understanding why an instance is predicted to be anomalous.

Anomaly Detection counterfactual

Learning Interpretable Concept Groups in CNNs

1 code implementation • 21 Sep 2021 • Saurabh Varshneya, Antoine Ledent, Robert A. Vandermeulen, Yunwen Lei, Matthias Enders, Damian Borth, Marius Kloft

We propose a novel training methodology -- Concept Group Learning (CGL) -- that encourages training of interpretable CNN filters by partitioning filters in each layer into concept groups, each of which is trained to learn a single visual concept.

Recognizing Challenging Handwritten Annotations with Fully Convolutional Networks

no code implementations • 1 Apr 2018 • Andreas Kölsch, Ashutosh Mishra, Saurabh Varshneya, Muhammad Zeshan Afzal, Marcus Liwicki

This paper introduces a very challenging dataset of historic German documents and evaluates Fully Convolutional Neural Network (FCNN) based methods to locate handwritten annotations of any kind in these documents.

Data Augmentation Semantic Segmentation