Skip to content
Calcrivo

CIDEr Score Calculator

Calculate the CIDEr score used to evaluate image captioning model outputs.

Inputs

CIDEr Score

7.2000

Scaled Similarity

7.2000

Step by step

  1. Average TF-IDF cosine similarity

    across 5 references

    = 0.7200

  2. CIDEr score (scaled ×10)

    0.7200 × 10

    = 7.2000

How it works

CIDEr (Consensus-based Image Description Evaluation) measures image captioning quality by computing TF-IDF weighted n-gram vectors for candidate and reference captions, then calculating their cosine similarity. It rewards captions that use words common in references but rare across the corpus, capturing consensus among annotators.

Formula

CIDEr

CIDEr_n = (1/M) * sum(cos_sim(tfidf_candidate, tfidf_ref_j)) * 10

M
Number of reference captions
cos_sim
Cosine similarity of TF-IDF vectors

Frequently Asked Questions

Why does CIDEr use TF-IDF weighting?

TF-IDF downweights common words (like 'the', 'a') and upweights informative words (like 'surfboard', 'sunset'), so CIDEr rewards captions that capture the distinctive content of an image rather than just generic descriptions.

Why is CIDEr multiplied by 10?

The scaling factor of 10 is a convention to make scores more readable — raw cosine similarities are typically between 0 and 1, so multiplying by 10 gives a more intuitive range.

You might also need