This paper deals with Generative Adversarial Networks (GANs) applied to face aging. An explainable face aging framework is proposed that builds on a well-known face aging approach, namely the Conditional Adversarial Autoencoder (CAAE). The proposed framework, namely, xAI-CAAE, couples CAAE with explainable Artificial Intelligence (xAI) methods, such as Saliency maps or Shapley additive explanations, to provide corrective feedback from the discriminator to the generator. xAI-guided training aims to supplement this feedback with explanations that provide a “reason” for the discriminator’s decision. Moreover, Local Interpretable Model-agnostic Explanations (LIME) are leveraged to provide explanations for the face areas that most influence the decision of a pre-trained age classifier. To the best of our knowledge, xAI methods are utilized in the context of face aging for the first time. A thorough qualitative and quantitative evaluation demonstrates that the incorporation of the xAI systems contributed significantly to the generation of more realistic age-progressed and regressed images.

The construction industry stands to greatly benefit from the technological advancements in deep learning and computer vision, which can automate time-consuming tasks such as quality control. In this paper, we introduce a framework that incorporates two advanced tools - the Visual Quality Control (VQC) tool and the Digital Twin visualization with Augmented Reality (DigiTAR) tool - to perform semi-automated visual quality control in the construction site during the execution phase of the project. The VQC tool is a backend service that detects potential defects on images captured on-site using the Mask R-CNN algorithm trained on annotated images of concrete and railway defects. The surveyor, aided by the Augmented Reality (AR) technology through the DigiTAR tool, can in-situ confirm/reject the detected defects and propose remedial actions. All the quality control results are recorded in the relevant BIM model and can be viewed on-site overlaid on the physical construction elements. This solution offers a semi-automated visual inspection that can speed up and simplify the quality control process, especially in case of large linear infrastructures, illustrating the added value of AR-based applications in Digital Twins

The construction industry stands to greatly benefit from the technological advancements in deep learning and computer vision, which can automate time-consuming tasks such as quality control. In this paper, we introduce a framework that incorporates two advanced tools - the Visual Quality Control (VQC) tool and the Digital Twin visualization with Augmented Reality (DigiTAR) tool - to perform semi-automated visual quality control in the construction site during the execution phase of the project. The VQC tool is a backend service that detects potential defects on images captured on-site using the Mask R-CNN algorithm trained on annotated images of concrete and railway defects. The surveyor, aided by the Augmented Reality (AR) technology through the DigiTAR tool, can in-situ confirm/reject the detected defects and propose remedial actions. All the quality control results are recorded in the relevant BIM model and can be viewed on-site overlaid on the physical construction elements. This solution offers a semi-automated visual inspection that can speed up and simplify the quality control process, especially in case of large linear infrastructures, illustrating the added value of AR-based applications in Digital Twins

This paper proposes a novel lightweight non-negative variant of Parallel Factor Analysis 2 (PARAFAC2), coined as LNN-PARAFAC2, that simultaneously enforces non-negativity and reduces computational complexity. Non-negativity is imposed through the application of Lagrange multipliers with multiplicative update rules. In parallel, the number of model parameters is reduced by imposing a diagonal structure on one of the common factor matrices, which reduces parameters from R² to R and lowers the per-iteration computational burden. Theoretical analysis establishes the uniqueness of the solution and convergence of the updates. To our knowledge, this is the first approach that integrates non-negativity into PARAFAC2 while also reducing computational complexity. Experimental results on toy examples and zero-shot cross-lingual document classification tasks validate the effectiveness of LNN-PARAFAC2, showing competitive or superior performance compared to existing non-negative PARAFAC2 methods, deep learning techniques, and PARAFAC2. LNN-PARAFAC2: https://github.com/iTsingalis/LNN-PARAFAC2.