AI engineering glossary · Evaluation metrics
What is CIDEr?
CIDEr (also called Consensus-based Image Description Evaluation): A metric for image captioning that compares a generated caption to several human captions using TF-IDF weighted n-gram similarity. Words common across all images get low weight, so distinctive, informative words that humans agree on drive the score.
CIDEr: an example
A caption 'a red auto-rickshaw on a busy road' scores well if several human captions also mention 'auto-rickshaw', a distinctive word, more than for generic words like 'a'.
Related terms
More Evaluation metrics terms
- Cohen's kappa
- Confusion matrix
- Continuous ranked probability score
- Cost matrix
- Cranfield paradigm
- Cumulative gains chart
- Davies-Bouldin index
- Diagnostic odds ratio
Where you learn it
CIDEr is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.