# An Examination of the Robustness of Reference-Free Image Captioning Evaluation Metrics

arXiv: https://arxiv.org/abs/2305.14998 · HTML: https://mlsanity.com/paper/2305.14998/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 42 references that are in the map.
- First posted on arXiv 24 May 2023.

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Object Hallucination in Image Captioning](https://mlsanity.com/paper/1809.02156/) (2018)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019)
- [Multi-Object Representation Learning with Iterative Variational Inference](https://mlsanity.com/paper/1903.00450/) (2019)
- [CREPE: Can Vision-Language Foundation Models Reason Compositionally?](https://mlsanity.com/paper/2212.07796/) (2022)
- [VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena](https://mlsanity.com/paper/2112.07566/) (2021)
- [FOIL it! Find One mismatch between Image and Language caption](https://mlsanity.com/paper/1705.01359/) (2017)
- [An Analysis of Visual Question Answering Algorithms](https://mlsanity.com/paper/1703.09684/) (2017)
- [Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation](https://mlsanity.com/paper/2303.12112/) (2023)
- [UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning](https://mlsanity.com/paper/2106.14019/) (2021)
- [InfoMetIC: An Informative Metric for Reference-free Image Caption Evaluation](https://mlsanity.com/paper/2305.06002/) (2023)
- [Reassessing Evaluation Practices in Visual Question Answering: A Case Study on Out-of-Distribution Generalization](https://mlsanity.com/paper/2205.12191/) (2022)
- [SMURF: SeMantic and linguistic UndeRstanding Fusion for Caption Evaluation via Typicality Analysis](https://mlsanity.com/paper/2106.01444/) (2021)
- [Weakly-Supervised Learning of Visual Relations in Multimodal Pretraining](https://mlsanity.com/paper/2305.14281/) (2023)

## Built on by (most cited first, 11 of 11)

- [Vision Language Model-based Caption Evaluation Method Leveraging Visual Context Extraction](https://mlsanity.com/paper/2402.17969/) (2024)
- [The Promise of RL for Autoregressive Image Editing](https://mlsanity.com/paper/2508.01119/) (2025)
- [The Intricate Dance of Prompt Complexity, Quality, Diversity, and Consistency in T2I Models](https://mlsanity.com/paper/2510.19557/) (2025)
- [Evaluation of Multilingual Image Captioning: How far can we get with CLIP models?](https://mlsanity.com/paper/2502.06600/) (2025)
- [Robust 3D-Masked Part-level Editing in 3D Gaussian Splatting with Regularized Score Distillation Sampling](https://mlsanity.com/paper/2507.11061/) (2025)
- [DiffuSyn Bench: Evaluating Vision-Language Models on Real-World Complexities with Diffusion-Generated Synthetic Benchmarks](https://mlsanity.com/paper/2406.04470/) (2024)
- [When More Words Say Less: Decoupling Length and Specificity in Image Description Evaluation](https://mlsanity.com/paper/2601.04609/) (2026)
- [Do Image-Text Metrics Respect Semantic Invariances?](https://mlsanity.com/paper/2605.24702/) (2026)
- [Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysis](https://mlsanity.com/paper/2408.04909/) (2024)
- [signwriting-evaluation: Effective Sign Language Evaluation via SignWriting](https://mlsanity.com/paper/2410.13668/) (2024)
- [MetaLogic: Robustness Evaluation of Text-to-Image Models via Logically Equivalent Prompts](https://mlsanity.com/paper/2510.00796/) (2025)

## Abstract (arXiv)

Recently, reference-free metrics such as CLIPScore (Hessel et al., 2021), UMIC (Lee et al., 2021), and PAC-S (Sarto et al., 2023) have been proposed for automatic reference-free evaluation of image captions. Our focus lies in evaluating the robustness of these metrics in scenarios that require distinguishing between two captions with high lexical overlap but very different meanings. Our findings reveal that despite their high correlation with human judgments, CLIPScore, UMIC, and PAC-S struggle to identify fine-grained errors. While all metrics exhibit strong sensitivity to visual grounding errors, their sensitivity to caption implausibility errors is limited. Furthermore, we found that all metrics are sensitive to variations in the size of image-relevant objects mentioned in the caption, while CLIPScore and PAC-S are also sensitive to the number of mentions of image-relevant objects in the caption. Regarding linguistic aspects of a caption, all metrics show weak comprehension of negation, and CLIPScore and PAC-S are insensitive to the structure of the caption to a great extent. We hope our findings will guide further improvements in reference-free evaluation of image captioning.