Redemption Score: A Multi-Modal Evaluation Framework for Image Captioning via Distributional, Perceptual, and Linguistic Signal Triangulation
Redemption Score is introduced, a novel evaluation framework for multi-modal generation by triangulating three complementary signals: Mutual Information Divergence for global image-text distributional alignment, DINO-based perceptual similarity of cycle-generated images for visual grounding, and LLM Text Embeddings for...