TISE: Bag of Metrics for Text-to-Image Synthesis Evaluation

TL;DR

This paper introduces TISE, a comprehensive evaluation framework with new metrics for assessing text-to-image synthesis, addressing current evaluation issues and providing more consistent, human-aligned rankings.

Contribution

It proposes a set of improved and new metrics for better evaluation of text-to-image models, including multi-object scenarios, and releases a benchmarking toolbox.

Findings

Enhanced metrics like IS* improve calibration accuracy.

New metrics for multi-object evaluation show better alignment with human judgment.

Benchmarking results demonstrate more consistent method rankings.

Abstract

In this paper, we conduct a study on the state-of-the-art methods for text-to-image synthesis and propose a framework to evaluate these methods. We consider syntheses where an image contains a single or multiple objects. Our study outlines several issues in the current evaluation pipeline: (i) for image quality assessment, a commonly used metric, e.g., Inception Score (IS), is often either miscalibrated for the single-object case or misused for the multi-object case; (ii) for text relevance and object accuracy assessment, there is an overfitting phenomenon in the existing R-precision (RP) and Semantic Object Accuracy (SOA) metrics, respectively; (iii) for multi-object case, many vital factors for evaluation, e.g., object fidelity, positional alignment, counting alignment, are largely dismissed; (iv) the ranking of the methods based on current metrics is highly inconsistent with real images. To overcome these issues, we propose a combined set of existing and new metrics to systematically evaluate the methods. For existing metrics, we offer an improved version of IS named IS* by using temperature scaling to calibrate the confidence of the classifier used by IS; we also propose a solution to mitigate the overfitting issues of RP and SOA. For new metrics, we develop counting alignment, positional alignment, object-centric IS, and object-centric FID metrics for evaluating the multi-object case. We show that benchmarking with our bag of metrics results in a highly consistent ranking among existing methods that is well-aligned with human evaluation. As a by-product, we create AttnGAN++, a simple but strong baseline for the benchmark by stabilizing the training of AttnGAN using spectral normalization. We also release our toolbox, so-called TISE, for advocating fair and consistent evaluation of text-to-image models.