VIFIDEL: Evaluating the Visual Fidelity of Image Descriptions (P19-1)

Copied to clipboard

Challenge: Existing methods for evaluating image description generation systems are subjective and expensive to scale.
Approach: They propose a new image-aware metric for evaluating image description generation systems . it estimates the faithfulness of a generated caption with respect to the content of the actual image .
Outcome: The proposed metric achieves high correlation with human judgments on two well-known datasets and is competitive with metrics that depend on and rely exclusively on human references.

Similar Papers

COSMic: A Coherence-Aware Generation Metric for Image Descriptions (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to evaluate captions have limited learning of their output . previous methods focused on n-gram measures of similarity to reference output based on a ngram of similarities to the output metric.
Approach: They propose a first discourse-aware learned generation metric for evaluating image descriptions.
Outcome: The proposed metric predicts human ratings of captions on out-of-domain images.
Transparent Human Evaluation for Image Captioning (2022.naacl-main)

Copied to clipboard

Challenge: Recent work has demonstrated that image captioning is a complex task that requires a large amount of human input.
Approach: They develop a human evaluation protocol for image captioning models based on machine- and human-generated captions on the MSCOCO dataset.
Outcome: The proposed model improves CLIPScore, a recent metric that uses image features, and improves human judgments because it is more sensitive to recall.
Towards Automatic Evaluation for Image Transcreation (2025.naacl-long)

Copied to clipboard

Challenge: Existing methods for evaluating image transcreation have relied on human evaluation.
Approach: They propose a suite of automatic evaluation metrics inspired by machine translation metrics . they identify cultural relevance, semantic equivalence and visual similarity as critical dimensions of image transcreation .
Outcome: The proposed evaluation metrics agree with human ratings across 7 countries.
Learning-based Composite Metrics for Improved Caption Evaluation (P18-3)

Copied to clipboard

Challenge: Existing image captioning metrics focus on linguistic aspects and do not match human judgements at sentence-level.
Approach: They propose to incorporate lexical and semantic metrics as features to capture adequacy and fluency of captions at different linguistic levels.
Outcome: The proposed framework captures adequacy and fluency of captions at different linguistic levels.
Towards Faithfully Interpretable NLP Systems: How Should We Define and Evaluate Faithfulness? (2020.acl-main)

Copied to clipboard

Challenge: Current approaches to interpretability evaluation focus on faithfulness criteria . current approaches focus on readability, plausibility and faithfulness .
Approach: They argue that current binary definition of faithfulness sets unrealistic standards . they argue that a more graded definition would be of greater practical utility .
Outcome: The proposed approach is based on three assumptions and lacks a graded definition of faithfulness.
EXPERT: An Explainable Image Captioning Evaluation Metric with Structured Explanations (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies on explainable evaluation metrics generate explanations without standardized criteria and the overall quality of the generated explanations remains unverified.
Approach: They propose a reference-free evaluation metric that provides structured explanations based on fluency, relevance, and descriptiveness.
Outcome: The proposed evaluation template achieves state-of-the-art on benchmark datasets while providing significantly higher-quality explanations than existing metrics.
TIGEr: Text-to-Image Grounding for Image Caption Evaluation (D19-1)

Copied to clipboard

Challenge: Existing metrics based on text-level comparisons fail to assess the quality of captions produced by machines.
Approach: They propose to use a machine-learned text-image grounding model to measure the accuracy of machine-generated captions and their correlation with human judgments.
Outcome: The proposed metric has higher consistency with human judgments and is more accurate than existing metrics.
Improving Image Captioning Evaluation by Considering Inter References Variance (2020.acl-main)

Copied to clipboard

Challenge: Existing one-to-one metrics penalize mismatches without considering the intrinsic variance between ground truth captions.
Approach: They propose a one-to-one metric based on BERTScore that could be extended to include new features for image captioning evaluation.
Outcome: The proposed metric achieves state-of-the-art human judgment correlation while improving performance.
CLIPScore: A Reference-free Evaluation Metric for Image Captioning (2021.emnlp-main)

Copied to clipboard

Challenge: Image captioning relies on reference-based automatic evaluations, but references are expensive to collect and comparing against multiple human-authored captions is insufficient.
Approach: They propose a reference-free metric that can be used for automatic caption evaluation without references.
Outcome: The proposed model outperforms existing metrics on image-text compatibility and a reference-augmented version achieves even higher correlation with human judgements.
FLEUR: An Explainable Reference-Free Evaluation Metric for Image Captioning Using a Large Multimodal Model (2024.acl-long)

Copied to clipboard

Challenge: Existing image captioning evaluation metrics do not provide an explanation for the assigned numerical score.
Approach: They propose an explainable reference-free metric to provide an explanation for captions . they introduce score smoothing to align as closely as possible with human judgment .
Outcome: The proposed metric achieves high correlations with human judgment across image captioning evaluation benchmarks and is publicly available at https://github.com/Yebin46/FLEUR.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations