CVPR 2024 NICE 挑战赛技术报告：使用集成 CLIP 与共识分数进行描述重排序评估
Technical Report of NICE Challenge at CVPR 2024: Caption Re-ranking Evaluation Using Ensembled CLIP and Consensus Scores
AI总结：
提出融合集成 CLIP 语义对齐分数与共识分数的 ECO 描述重排序框架，并在 CVPR 2024 NICE 挑战赛多项指标中取得领先名次。
摘要：
本报告介绍了 DSBA LAB 团队的 ECO（Ensembled Clip score and cOnsensus score，集成 CLIP 分数与共识分数）流程，这是一个用于评估给定图像的描述并对其进行排序的新框架。ECO 通过结合集成 CLIP 分数与共识分数，选出最准确描述图像的描述文本；前者考虑图像与描述之间的语义对齐，后者衡量描述的本质性。借助该框架，我们在 CVPR 2024“零样本图像描述评估新前沿”（NICE）研讨会的描述重排序评估挑战赛中取得了显著成功。具体而言，我们在 CIDEr 指标上获得第三名，在 SPICE 和 METEOR 指标上均获得第二名，并在 ROUGE-L 以及所有 BLEU Score 指标上获得第一名。ECO 框架的代码和配置可在 https://github.com/DSBA-Lab/ECO 获取。
英文摘要：
This report presents the ECO (Ensembled Clip score and cOnsensus score) pipeline from team DSBA LAB, which is a new framework used to evaluate and rank captions for a given image. ECO selects the most accurate caption describing image. It is made possible by combining an Ensembled CLIP score, which considers the semantic alignment between the image and captions, with a Consensus score that accounts for the essentialness of the captions. Using this framework, we achieved notable success in the CVPR 2024 Workshop Challenge on Caption Re-ranking Evaluation at the New Frontiers for Zero-Shot Image Captioning Evaluation (NICE). Specifically, we secured third place based on the CIDEr metric, second in both the SPICE and METEOR metrics, and first in the ROUGE-L and all BLEU Score metrics. The code and configuration for the ECO framework are available at https://github.com/DSBA-Lab/ECO .
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
