
The author proposes Polos, a supervised automatic evaluation metric for image captioning models, utilizing a parallel feature extraction mechanism and human feedback. The approach aims to address the limitations of existing metrics by incorporating multimodal inputs and large-scale contrastive learning.


coremsg

Polos-Multimodal-Metric-Learning-for-Image-Captioning


Polos: Multimodal Metric Learning for Image Captioning


title_rewrite


Polos is a novel automatic evaluation metric for image captioning models that outperforms existing metrics by leveraging multimodal inputs and human feedback.


polos-multimodal-metric-learning-for-image-captioning-evaluation


Polos: Multimodal Metric Learning for Image Captioning Evaluation
