Correlation of Self-Supervised Signal Quality and Captioning BLEU Scores in Low-Resource Domains

Image captioning, a fundamental task in vision-language understanding, seeks to generate accurate natural language descriptions for provided images. Current image captioning approaches heavily rely on high-quality image-caption pairs, which can be hard to obtain for many domains. To address this, we introduce a self-supervised image captioning method. After learning an initial signal from a small labeled dataset, our method transitions to self-supervised learning on unlabeled data, leveraging the auxiliary task of enhancing the CLIP relevance between images and generated captions. Remarkably,

Research goal: What is the correlation between self-supervised signal quality from small labeled datasets and final captioning BLEU scores in low-resource domains?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 9.3/10.