Pros and cons of GAN evaluation measures: New developments
A Borji - Computer Vision and Image Understanding, 2022 - Elsevier
This work is an update of my previous paper on the same topic published a few years ago
(Borji, 2019). With the dramatic progress in generative modeling, a suite of new quantitative …
(Borji, 2019). With the dramatic progress in generative modeling, a suite of new quantitative …
Generating a novel synthetic dataset for rehabilitation exercises using pose-guided conditioned diffusion models: A quantitative and qualitative evaluation
C Mennella, U Maniscalco, G De Pietro… - Computers in Biology …, 2023 - Elsevier
Abstract Machine learning has emerged as a promising approach to enhance rehabilitation
therapy monitoring and evaluation, providing personalized insights. However, the scarcity of …
therapy monitoring and evaluation, providing personalized insights. However, the scarcity of …
Quantifying Explainability with Multi-Scale Gaussian Mixture Models
With the increasing complexity and influence of machine learning models the development
of model explanation techniques has recently gained significant attention giving rise to the …
of model explanation techniques has recently gained significant attention giving rise to the …
Quantum diffusion models
We propose a quantum version of a generative diffusion model. In this algorithm, artificial
neural networks are replaced with parameterized quantum circuits, in order to directly …
neural networks are replaced with parameterized quantum circuits, in order to directly …
Wavelet Packet Power Spectrum Kullback-Leibler Divergence: A New Metric for Image Synthesis
Current metrics for generative neural networks are biased towards low frequencies, specific
generators, objects from the ImageNet dataset, and value texture more than shape. Many …
generators, objects from the ImageNet dataset, and value texture more than shape. Many …
Gromov-Wassertein-like Distances in the Gaussian Mixture Models Space
In this paper, we introduce two Gromov-Wasserstein-type distances on the set of Gaussian
mixture models. The first one takes the form of a Gromov-Wasserstein distance between two …
mixture models. The first one takes the form of a Gromov-Wasserstein distance between two …
Objective Evaluation Metric for Motion Generative Models: Validating Fréchet Motion Distance on Foot Skating and Over-smoothing Artifacts.
Nowadays, Deep Learning-powered generative models are able to generate new synthetic
samples nearly indistinguishable from natural data. The development of such systems …
samples nearly indistinguishable from natural data. The development of such systems …
Geometry Fidelity for Spherical Images
A Christensen, N Mojab, K Patel, K Ahuja… - arXiv preprint arXiv …, 2024 - arxiv.org
Spherical or omni-directional images offer an immersive visual format appealing to a wide
range of computer vision applications. However, geometric properties of spherical images …
range of computer vision applications. However, geometric properties of spherical images …
Unifying and extending Precision Recall metrics for assessing generative models
B Sykes, L Simon, J Rabin - arXiv preprint arXiv:2405.01611, 2024 - arxiv.org
With the recent success of generative models in image and text, the evaluation of generative
models has gained a lot of attention. Whereas most generative models are compared in …
models has gained a lot of attention. Whereas most generative models are compared in …
Validating Objective Evaluation Metric: Is Fréchet Motion Distance able to Capture Foot Skating Artifacts?
Automatically generating character motion is one of the technologies required for virtual
reality, graphics, and robotics. Motion synthesis with deep learning is an emerging research …
reality, graphics, and robotics. Motion synthesis with deep learning is an emerging research …