Semantic prioritization in visual counterfactual explanations with weighted segmentation and auto-adaptive region selection
In the domain of non-generative visual counterfactual explanations (CE), traditional
techniques frequently involve the substitution of sections within a query image with …
techniques frequently involve the substitution of sections within a query image with …
Mechanistic understanding and validation of large AI models with SemanticLens
Unlike human-engineered systems such as aeroplanes, where each component's role and
dependencies are well understood, the inner workings of AI models remain largely opaque …
dependencies are well understood, the inner workings of AI models remain largely opaque …
Flow AM: Generating Point Cloud Global Explanations by Latent Alignment
H Tan - arXiv preprint arXiv:2404.18760, 2024 - arxiv.org
Although point cloud models have gained significant improvements in prediction accuracy
over recent years, their trustworthiness is still not sufficiently investigated. In terms of global …
over recent years, their trustworthiness is still not sufficiently investigated. In terms of global …
Associative Interpretability of Hidden Semantics with Contrastiveness Operators in Face Classification Tasks
F Aguilar-Canto, O García-Vásquez, T Alcántara… - World Conference on …, 2024 - Springer
The development of Hebbian-based architectures is motivated by the necessity for online
learning algorithms in Artificial Neural Networks (ANNs) and other biologically inspired …
learning algorithms in Artificial Neural Networks (ANNs) and other biologically inspired …