CIDEr-R: Robust Consensus-based Image Description Evaluation

Autor:	Santos, Gabriel Oliveira dos, Colombini, Esther Luna, Avila, Sandra
Rok vydání:	2021
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	This paper shows that CIDEr-D, a traditional evaluation metric for image description, does not work properly on datasets where the number of words in the sentence is significantly greater than those in the MS COCO Captions dataset. We also show that CIDEr-D has performance hampered by the lack of multiple reference sentences and high variance of sentence length. To bypass this problem, we introduce CIDEr-R, which improves CIDEr-D, making it more flexible in dealing with datasets with high sentence length variance. We demonstrate that CIDEr-R is more accurate and closer to human judgment than CIDEr-D; CIDEr-R is more robust regarding the number of available references. Our results reveal that using Self-Critical Sequence Training to optimize CIDEr-R generates descriptive captions. In contrast, when CIDEr-D is optimized, the generated captions' length tends to be similar to the reference length. However, the models also repeat several times the same word to increase the sentence length. Comment: Paper accepted to the 7th Workshop on Noisy User-generated Text (W-NUT). 10 pages, 4 figures, 3 tables
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2109.13701 Zobrazit plný text záznamu View this record from Arxiv