Technical Report of NICE Challenge at CVPR 2024: Caption Re-ranking Evaluation Using Ensembled CLIP and Consensus Scores
This work addresses caption re-ranking for zero-shot image captioning evaluation, presenting an incremental improvement through a novel hybrid method.
The paper tackles the problem of selecting the most accurate caption for an image by introducing the ECO pipeline, which combines an Ensembled CLIP score and a Consensus score, achieving third place in CIDEr, second in SPICE and METEOR, and first in ROUGE-L and all BLEU scores in the CVPR 2024 NICE Challenge.
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 .