“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI

IEEE Transactions on Pattern Analysis and Machine Intelligence

A morphable model for the synthesis of 3D faces

In the last years, Artificial Intelligence (AI) has achieved a notable momentum that may deliver the best of expectations over many application sectors across the field. For this to occur, the entire community stands in front of the barrier of explainability, an inherent problem of AI techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI. Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is acknowledged as a crucial feature for the practical deployment of AI models. This overview examines the existing literature in the field of XAI, including a prospect toward what is yet to be reached. We summarize previous efforts to define explainability in Machine Learning, establishing a novel definition that covers prior conceptual propositions with a major focus on the audience for which explainability is sought. We then propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at Deep Learning methods for which a second taxonomy is built. This literature analysis serves as the background for a series of challenges faced by XAI, such as the crossroads between data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to XAI with a reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI.

In this supplemental document, we provide a detailed derivation of the OLAT decomposition and the face reflectance fields in Sec. 1. We then provide a summary of related works in Sec. 2, to better highlight our work with respect to the literature. In Sec. 3 we provide the detailed network architectures of our Face Prior Network and our Reflectance Network . Further, we discuss the lightstage dataset used to train our method in Sec. 4. Implementation details are given in Sec. 5, where we also show additional results on relighting and viewpoint synthesis of our method, with different numbers of input views. We also discuss the failures of baseline methods (PhotoApp in Sec. 6, NeLF in Sec. 7). In Sec. 8 we showcase our intermediate OLAT results. Furthermore, in Sec. 9 we provide a detailed ablative study on various design choices of our proposed solution. In Sec. 10 we analyze the limitations of our proposed method. In addition to this supplemental document,

VoRF: Volumetric Relightable Faces Friedrich-Alexander-UniversitätErlangen-Nürnberg(FAU),Germany

Denoising diffusion models are a powerful type of generative models used to capture complex distributions of real-world signals. However, their applicability is limited to scenarios where training samples are readily available, which is not always the case in real-world applications. For example, in inverse graphics, the goal is to generate samples from a distribution of 3D scenes that align with a given image, but ground-truth 3D scenes are unavailable and only 2D images are accessible. To address this limitation, we propose a novel class of denoising diffusion probabilistic models that learn to sample from distributions of signals that are never directly observed. Instead, these signals are measured indirectly through a known differentiable forward model, which produces partial observations of the unknown signal. Our approach involves integrating the forward model directly into the denoising process. This integration effectively connects the generative modeling of observations with the generative modeling of the underlying signals, allowing for end-to-end training of a conditional generative model over signals. During inference, our approach enables sampling from the distribution of underlying signals that are consistent with a given partial observation. We demonstrate the effectiveness of our method on three challenging computer vision tasks. For instance, in the context of inverse graphics, our model enables direct sampling from the distribution of 3D scenes that align with a single 2D input image.

Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision

Abstract We provide a new forbidden criterion for the realizability of smooth tropical plane curves. This in turn provides us a complete classification of smooth tropical plane curves up to genus six. 

https://link.springer.com/content/pdf/10.1007/s00013-023-01842-5.pdf

Ayush Tewari

Papers

VoRF: Volumetric Relightable Faces Friedrich-Alexander-UniversitätErlangen-Nürnberg(FAU),Germany

Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision

Characterization of tropical plane curves up to genus six