Instruction-augmented Multimodal Alignment for Image-Text and Element Matching
Authors:
Preprint
Abstract
With the rapid advancement of text-to-image (T2I) generation models, assessing the semantic alignment between generated images and text descriptions has become a significant research challenge. Current methods, including those based on Visual Question Answering (VQA), still struggle with fine-grained assessments and precise quantification of image-text alignment. This paper presents an improved evaluation method named Instruction-augmented Multimodal Alignment for Image-Text and Element Matching (iMatch), which evaluates image-text semantic alignment by fine-tuning multimodal large language models. We introduce four innovative augmentation strategies: First, the QAlign strategy creates a precise probabilistic mapping to convert discrete scores from multimodal large language models into continuous matching scores. Second, a validation set augmentation strategy uses pseudo-labels from model predictions to expand training data, boosting the model's generalization performance. Third, an element augmentation strategy integrates element category labels to refine the model's understanding of image-text matching. Fourth, an image augmentation strategy employs techniques like random lighting to increase the model's robustness. Additionally, we propose prompt type augmentation and score perturbation strategies to further enhance the accuracy of element assessments. Our experimental results show that the iMatch method significantly surpasses existing methods, confirming its effectiveness and practical value. Furthermore, our iMatch won first place in the CVPR NTIRE 2025 Text to Image Generation Model Quality Assessment - Track 1 Image-Text Alignment.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- EvalMuse-40K: A Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Alignment EvaluationProceedings of the AAAI Conference on Artificial Intelligence, 2026
- SWIFT: A Scalable Lightweight Infrastructure for Fine-TuningProceedings of the AAAI Conference on Artificial Intelligence, 2025
- MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image SynthesisProceedings of the AAAI Conference on Artificial Intelligence, 2025
- Adversarial Diffusion Distillation2024
- Evaluating and Improving Compositional Text-to-Visual Generation2024
- Improved Baselines with Visual Instruction Tuning2024
- Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following2024
- TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering2023
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- CLIPScore: A Reference-free Evaluation Metric for Image Captioning2021