SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation
arXiv · · Significant research
Summary
Researchers from MBZUAI have introduced SPECS, a new reference-free evaluation metric for long image captions that modifies CLIP to emphasize specificity. SPECS aims to improve the correlation with human judgment while maintaining computational efficiency compared to LLM-based metrics. The proposed approach is intended for iterative use during image captioning model development, offering a practical alternative to existing methods.
Keywords
image captioning · evaluation metric · CLIP · specificity · SPECS
Get the weekly digest
Top AI stories from the GCC region, every week.