Improving the Evaluation of Generative Models with Fuzzy Logic

2020/02/03 by Julian Niedermeier, Niedermeier, Julian, Gonçalo Mordido +3 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · #Advanced Image and Video Retrieval Techniques #Cell Image Analysis Techniques #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2002.03772

openalex publication_date 2020/02/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Objective and interpretable metrics to evaluate current artificial intelligent systems are of great importance, not only to analyze the current state of such systems but also to objectively measure progress in the future. In this work, we focus on the evaluation of image generation tasks. We propose a novel approach, called Fuzzy Topology Impact (FTI), that determines both the quality and diversity of an image set using topology representations combined with fuzzy logic. When compared to current evaluation methods, FTI shows better and more stable performance on multiple experiments evaluating the sensitivity to noise, mode dropping and mode inventing.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Assessing Generative Models via Precision and Recall
• Learning Multiple Layers of Features from Tiny Images

Cited by

• Fuzzy Generative Adversarial Networks

Related

• Fuzzy Theory in Computer Vision: A Review
• An Improved Evaluation Framework for Generative Adversarial Networks
• Barcode Method for Generative Model Evaluation driven by Topological Data Analysis
• Reliable Fidelity and Diversity Metrics for Generative Models
• Approximating Human Judgment of Generated Image Quality