5 papers
WasteAssistant: Regulation-Guided Visual Question Answering Framework for Intelligent Waste Segregation and Sustainable Managemen
Khush Kataruka, Harshit Maurya, Anuja Vats +3
Efficient waste segregation is critical for sustainable urban management and environmental governance. Existing automated systems are limited by single-modality visual processing,…
Target-confidence Recourse Using tSeTlin machines: TRUST
K. Darshana Abeyrathna, Sara El Mekkaoui, Nils Enric Canut Taugbøl +1
Counterfactual explanations are widely used to provide algorithmic recourse in high-stakes decision-making systems. Most existing methods seek the smallest change to an input that…
Chaotic Map based Compression Approach to Classification
Harikrishnan N B, Anuja Vats, Nithin Nagaraj +1
Modern machine learning approaches often prioritize performance at the cost of increased complexity, computational demands, and reduced interpretability. This paper introduces a no…
Influence of color correction on pathology detection in Capsule Endoscopy
Bidossessi Emmanuel Agossou, Marius Pedersen, Kiran Raja +2
Pathology detection in Wireless Capsule Endoscopy (WCE) using deep learning has been explored in the recent past. However, deep learning models can be influenced by the color quali…
Uncertainty-Aware Regularization for Image-to-Image Translation
Anuja Vats, Ivar Farup, Marius Pedersen +1
The importance of quantifying uncertainty in deep networks has become paramount for reliable real-world applications. In this paper, we propose a method to improve uncertainty esti…