SPICE Evaluator

I broke down SPICE because I couldn’t find a solid visual of how it scores captions. The SPICE & Scene-Graph Evaluation Dashboard is an end-to-end tool for assessing image captions, combining the official SPICE metric with interactive, force-directed visualizations of object–relation–object and object–attribute tuples.

How SPICE Works

SPICE (Semantic Propositional Image Caption Evaluation) measures how well a candidate caption captures the same meaning as one or more reference captions by breaking each sentence into atomic "facts" and comparing them. It proceeds in four main stages:

1. Dependency Parsing

• Each caption is processed by Stanford CoreNLP, which performs tokenization, part-of-speech tagging, and builds a dependency parse tree.
• The tree makes explicit grammatical relationships (e.g., which word is the subject of a verb, which adjective modifies which noun).

2. Semantic Tuple Extraction

• From the dependency tree, SPICE extracts two types of tuples:
  • Object–Attribute pairs, e.g. ("dog", "brown")
  • Subject–Relation–Object triples, e.g. ("dog", "running_in", "park")
• Each tuple represents a single, discrete proposition about the scene described.

3. Tuple Alignment with WordNet

• SPICE aligns the candidate's tuples with those from the reference(s):
  1. Exact string match (e.g. "park" ↔ "park")
  2. WordNet synonym match when labels differ (e.g. "dog" ↔ "canine")
• This ensures semantically equivalent facts are paired—even if different words are used.
• Tool reveals the raw tuples it found in your captions.


4. Precision, Recall & F₁ Computation

• Precision = matched candidate tuples ÷ total candidate tuples
• Recall = matched reference tuples ÷ total reference tuples
• F₁ = 2 × (Precision × Recall) ÷ (Precision + Recall)
• These scores reflect how accurately (precision) and completely (recall) the candidate caption covers the reference's semantic content, with F₁ as the harmonic mean.

Once tuples are extracted, they can be viewed as an interactive scene graph.

• Nodes represent objects or attributes.
• Edges represent relations or the "has_attr" link.

Tech Stack

• Python & Streamlit: Backend orchestration and web UI.
• Java & Stanford CoreNLP: SPICE-1.0 computation and scene-graph parsing.
• PyVis & NetworkX: Building interactive force-directed graph layouts.
• NLTK WordNet: Optional synonym matching for tuple-level evaluation.
• Conda: Manages the Python 3.11.8 environment.

Installation & Setup

For detailed installation and setup instructions, please refer to the instructions in the SPICE-Evaluator repository.

References

[1] P. Anderson, B. Fernando, M. Johnson, and S. Gould, "SPICE: Semantic Propositional Image Caption Evaluation," arXiv preprint arXiv:1607.08822, Jul. 2016. [Online]. Available: https://arxiv.org/abs/1607.08822

For full code, examples, and configuration, see the SPICE-Evaluator GitHub Repository.