A Lightweight Generalizable Evaluation and Enhancement Framework for Generative Models and Generated Samples

Ganning Zhao, Vasileios Magoulianitis, Suya You, C.-C. Jay Kuo; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, 2024, pp. 450-459

While extensive research has been conducted on evaluating generative models, little research has been conducted on the quality assessment and enhancement of individual-generated samples. We propose a lightweight generalizable evaluation framework, designed to evaluate and enhance the generative models and generated samples. Our framework trains a classifier-based dataset-specific model, enabling its application to unseen generative models and extending its compatibility with both deep learning and efficient machine learning-based methods. We propose three novel evaluation metrics aiming at capturing distribution correlation, quality, and diversity of generated samples. These metrics collectively offer a more thorough performance evaluation of generative models compared to the Frechet Inception Distance (FID). Our approach assigns individual quality scores to each generated sample for sample-level evaluation. This enables better sample mining and thereby improves the performance of generative models by filtering out lower-quality generations. Extensive experiments across various datasets and generative models demonstrate the effectiveness and efficiency of the proposed method.