Ordinal Prompt-Regularized Graph Optimal Transport for Image Ordinal Estimation

This paper proposes a novel approach for image ordinal estimation, leveraging the power of Optimal Transport (OT) and prompt learning. Traditional ordinal regression methods primarily focus on learning a model to predict numerical scores, which may not directly reflect the intrinsic order. To address this limitation, we introduce a framework, termed Ordinal Prompt-regularized Graph Optimal Transport (OPGOT), which utilizes OT to align the distribution of images and that of ordinal labels. First, we incorporate prompt learning with pre-trained text encoders to construct ordinal prompts through a token-wise distance-based weighting scheme, enabling the model to capture the semantic relationships between ordinal categories. Second, the OPGOT matches the graphs of image features and prompt embeddings via optimizing the OT with language-image cost. Hence, the learned transport plan reflects the intrinsic ordinal relationships. We conduct extensive evaluations on four benchmark datasets of different scenarios, demonstrating that OPGOT achieves significant improvements against existing methods.