6 papers
EMERGE: Resolution-Agnostic Point Cloud Generation with Equivariant Graph-Based Diffusion
Ilias Mitsouras, Nikolaos Chaidos, Giorgos Stamou +1
Point cloud generation has emerged as a crucial task for accurately capturing and reproducing the complexity of the physical world. However, existing generative approaches, predomi…
U-CECE: A Universal Multi-Resolution Framework for Conceptual Counterfactual Explanations
Angeliki Dimitriou, Nikolaos Chaidos, Maria Lymperaiou +2
As AI models grow more complex, explainability is essential for building trust, yet concept-based counterfactual methods still face a trade-off between expressivity and efficiency.…
Through the PRISm: Importance-Aware Scene Graphs for Semantic Image Retrieval
Dimitrios Georgoulopoulos, Nikolaos Chaidos, Angeliki Dimitriou +1
Web-based visual search increasingly handles queries driven by semantic intent, focusing on what is happening in an image rather than merely what it looks like. While global embedd…
SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval
Nikolaos Chaidos, Angeliki Dimitriou, Maria Lymperaiou +1
Despite the dominance of convolutional and transformer-based architectures in image-to-image retrieval, these models are prone to biases arising from low-level visual features, suc…
Explaining Vision GNNs: A Semantic and Visual Analysis of Graph-based Image Classification
Nikolaos Chaidos, Angeliki Dimitriou, Nikolaos Spanos +2
Graph Neural Networks (GNNs) have emerged as an efficient alternative to convolutional approaches for vision tasks such as image classification, leveraging patch-based representati…
Graph Edits for Counterfactual Explanations: A comparative study
Angeliki Dimitriou, Nikolaos Chaidos, Maria Lymperaiou +1
Counterfactuals have been established as a popular explainability technique which leverages a set of minimal edits to alter the prediction of a classifier. When considering concept…