Logo image
WEmbSim: A simple yet effective metric for image captioning
Conference paper

WEmbSim: A simple yet effective metric for image captioning

N. Sharif, L. White, M. Bennamoun, W. Liu and S.A.A. Shah
2020 Digital Image Computing: Techniques and Applications (DICTA)
2020 Digital Image Computing: Techniques and Applications (DICTA) (Melbourne, Australia, 29/11/2020–02/12/2020)
2020
url
Link to Published Version *Subscription may be requiredView

Abstract

The area of automatic image caption evaluation is still undergoing intensive research to address the needs of generating captions which can meet adequacy and fluency requirements. Based on our past attempts at developing highly sophisticated learning-based metrics, we have discovered that a simple cosine similarity measure using the Mean of Word Embeddings (MOWE) of captions can actually achieve a surprisingly high performance on unsupervised caption evaluation. This inspires our proposed work on an effective metric WEmbSim, which beats complex measures such as SPICE, CIDEr and WMD at system-level correlation with human judgments. Moreover, it also achieves the best accuracy at matching human consensus scores for caption pairs, against commonly used unsupervised methods. Therefore, we believe that WEmbSim sets a new baseline for any complex metric to be justified.

Details

Metrics

90 Record Views
Logo image