Skip to content
Calcrivo

SPICE Score Calculator

Calculate the SPICE score for evaluating semantic content in image captions.

Inputs

SPICE Score

0.7273

Precision

0.8000

Recall

0.6667

Step by step

  1. Precision: matched ÷ candidate tuples

    12 ÷ 15

    = 0.8000

  2. Recall: matched ÷ reference tuples

    12 ÷ 18

    = 0.6667

  3. SPICE (F1): 2PR/(P+R)

    2×0.8000×0.6667/(0.8000+0.6667)

    = 0.727273

How it works

SPICE (Semantic Propositional Image Caption Evaluation) evaluates caption quality by parsing both candidate and reference captions into scene graphs (objects, attributes, relations), then computing F1 over matched tuples. Unlike n-gram metrics, SPICE directly evaluates semantic content regardless of wording.

Formula

SPICE

SPICE = F1(matched_tuples, candidate_tuples, reference_tuples)

tuples
Scene graph tuples: (object, attribute) or (subject, relation, object)

Frequently Asked Questions

How does SPICE differ from CIDEr?

CIDEr uses TF-IDF n-gram overlap (lexical matching), while SPICE parses captions into semantic scene graphs and matches meaning directly. SPICE better captures whether the caption correctly describes objects, attributes, and their relationships.

What are scene graph tuples?

Scene graph tuples represent semantic content: objects ('dog', 'ball'), attributes ('red', 'large'), and relations ('chasing', 'on top of'). They're extracted by parsing captions using dependency parsing and semantic role labeling.

You might also need