SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Xiaofu, Salazar, Israfel, Kementchedjhieva, Yova
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911151029223424
author Chen, Xiaofu
Salazar, Israfel
Kementchedjhieva, Yova
author_facet Chen, Xiaofu
Salazar, Israfel
Kementchedjhieva, Yova
contents As interest grows in generating long, detailed image captions, standard evaluation metrics become increasingly unreliable. N-gram-based metrics though efficient, fail to capture semantic correctness. Representational Similarity (RS) metrics, designed to address this, initially saw limited use due to high computational costs, while today, despite advances in hardware, they remain unpopular due to low correlation to human judgments. Meanwhile, metrics based on large language models (LLMs) show strong correlation with human judgments, but remain too expensive for iterative use during model development. We introduce SPECS (Specificity-Enhanced CLIPScore), a reference-free RS metric tailored to long image captioning. SPECS modifies CLIP with a new objective that emphasizes specificity: rewarding correct details and penalizing incorrect ones. We show that SPECS matches the performance of open-source LLM-based metrics in correlation to human judgments, while being far more efficient. This makes it a practical alternative for iterative checkpoint evaluation during image captioning model development.Our code can be found at https://github.com/mbzuai-nlp/SPECS.
format Preprint
id arxiv_https___arxiv_org_abs_2509_03897
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation
Chen, Xiaofu
Salazar, Israfel
Kementchedjhieva, Yova
Computer Vision and Pattern Recognition
Computation and Language
As interest grows in generating long, detailed image captions, standard evaluation metrics become increasingly unreliable. N-gram-based metrics though efficient, fail to capture semantic correctness. Representational Similarity (RS) metrics, designed to address this, initially saw limited use due to high computational costs, while today, despite advances in hardware, they remain unpopular due to low correlation to human judgments. Meanwhile, metrics based on large language models (LLMs) show strong correlation with human judgments, but remain too expensive for iterative use during model development. We introduce SPECS (Specificity-Enhanced CLIPScore), a reference-free RS metric tailored to long image captioning. SPECS modifies CLIP with a new objective that emphasizes specificity: rewarding correct details and penalizing incorrect ones. We show that SPECS matches the performance of open-source LLM-based metrics in correlation to human judgments, while being far more efficient. This makes it a practical alternative for iterative checkpoint evaluation during image captioning model development.Our code can be found at https://github.com/mbzuai-nlp/SPECS.
title SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2509.03897