CROC: Evaluating and Training T2I Metrics with Pseudo- and Human-Labeled Contrastive Robustness Checks

• URL: http://arxiv.org/abs/2505.11314v1
• Date: Fri, 16 May 2025 14:39:44 GMT
• Title: CROC: Evaluating and Training T2I Metrics with Pseudo- and Human-Labeled Contrastive Robustness Checks
• Authors: Christoph Leiter, Yuki M. Asano, Margret Keuper, Steffen Eger,
• Abstract summary: We propose CROC: a framework for automated Contrastive Robustness Checks.<n>We generate a pseudo-labeled dataset of over one million contrastive prompt-image pairs.<n>We also use the dataset to train CROCScore, a new metric that achieves state-of-the-art performance among open-source methods.
• Score: 46.89839054706183
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The assessment of evaluation metrics (meta-evaluation) is crucial for determining the suitability of existing metrics in text-to-image (T2I) generation tasks. Human-based meta-evaluation is costly and time-intensive, and automated alternatives are scarce. We address this gap and propose CROC: a scalable framework for automated Contrastive Robustness Checks that systematically probes and quantifies metric robustness by synthesizing contrastive test cases across a comprehensive taxonomy of image properties. With CROC, we generate a pseudo-labeled dataset (CROC$^{syn}$) of over one million contrastive prompt-image pairs to enable a fine-grained comparison of evaluation metrics. We also use the dataset to train CROCScore, a new metric that achieves state-of-the-art performance among open-source methods, demonstrating an additional key application of our framework. To complement this dataset, we introduce a human-supervised benchmark (CROC$^{hum}$) targeting especially challenging categories. Our results highlight robustness issues in existing metrics: for example, many fail on prompts involving negation, and all tested open-source metrics fail on at least 25% of cases involving correct identification of body parts.

Related papers

• Exploring Information Retrieval Landscapes: An Investigation of a Novel Evaluation Techniques and Comparative Document Splitting Methods [0.0]
  In this study, the structured nature of textbooks, the conciseness of articles, and the narrative complexity of novels are shown to require distinct retrieval strategies. A novel evaluation technique is introduced, utilizing an open-source model to generate a comprehensive dataset of question-and-answer pairs. The evaluation employs weighted scoring metrics, including SequenceMatcher, BLEU, METEOR, and BERT Score, to assess the system's accuracy and relevance.
  arXiv  Detail & Related papers  (2024-09-13T02:08:47Z)
• RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework [66.93260816493553]
  This paper introduces RAGEval, a framework designed to assess RAG systems across diverse scenarios.<n>With a focus on factual accuracy, we propose three novel metrics: Completeness, Hallucination, and Irrelevance.<n> Experimental results show that RAGEval outperforms zero-shot and one-shot methods in terms of clarity, safety, conformity, and richness of generated samples.
  arXiv  Detail & Related papers  (2024-08-02T13:35:11Z)
• DCR-Consistency: Divide-Conquer-Reasoning for Consistency Evaluation and Improvement of Large Language Models [4.953092503184905]
  This work proposes DCR, an automated framework for evaluating and improving the consistency of Large Language Models (LLMs) generated texts. We introduce an automatic metric converter (AMC) that translates the output from DCE into an interpretable numeric score. Our approach also substantially reduces nearly 90% of output inconsistencies, showing promise for effective hallucination mitigation.
  arXiv  Detail & Related papers  (2024-01-04T08:34:16Z)
• Bring Your Own Data! Self-Supervised Evaluation for Large Language Models [52.15056231665816]
  We propose a framework for self-supervised evaluation of Large Language Models (LLMs) We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence. We find strong correlations between self-supervised and human-supervised evaluations.
  arXiv  Detail & Related papers  (2023-06-23T17:59:09Z)
• From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework [91.94389491920309]
  Textual adversarial attacks can discover models' weaknesses by adding semantic-preserved but misleading perturbations to the inputs. The existing practice of robustness evaluation may exhibit issues of incomprehensive evaluation, impractical evaluation protocol, and invalid adversarial samples. We set up a unified automatic robustness evaluation framework, shifting towards model-centric evaluation to exploit the advantages of adversarial attacks.
  arXiv  Detail & Related papers  (2023-05-29T14:55:20Z)
• GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models [60.48306899271866]
  We present a new framework, called GREAT Score, for global robustness evaluation of adversarial perturbation using generative models. We show high correlation and significantly reduced cost of GREAT Score when compared to the attack-based model ranking on RobustBench. GREAT Score can be used for remote auditing of privacy-sensitive black-box models.
  arXiv  Detail & Related papers  (2023-04-19T14:58:27Z)
• Evaluating and Improving Factuality in Multimodal Abstractive Summarization [91.46015013816083]
  We propose CLIPBERTScore to leverage the robustness and strong factuality detection performance between image-summary and document-summary. We show that this simple combination of two metrics in the zero-shot achieves higher correlations than existing factuality metrics for document summarization. Our analysis demonstrates the robustness and high correlation of CLIPBERTScore and its components on four factuality metric-evaluation benchmarks.
  arXiv  Detail & Related papers  (2022-11-04T16:50:40Z)
• Utilizing Class Separation Distance for the Evaluation of Corruption Robustness of Machine Learning Classifiers [0.6882042556551611]
  We propose a test data augmentation method that uses a robustness distance $epsilon$ derived from the datasets minimal class separation distance. The resulting MSCR metric allows a dataset-specific comparison of different classifiers with respect to their corruption robustness. Our results indicate that robustness training through simple data augmentation can already slightly improve accuracy.
  arXiv  Detail & Related papers  (2022-06-27T15:56:16Z)
• TRUE: Re-evaluating Factual Consistency Evaluation [29.888885917330327]
  We introduce TRUE: a comprehensive study of factual consistency metrics on a standardized collection of existing texts from diverse tasks. Our standardization enables an example-level meta-evaluation protocol that is more actionable and interpretable than previously reported correlations. Across diverse state-of-the-art metrics and 11 datasets we find that large-scale NLI and question generation-and-answering-based approaches achieve strong and complementary results.
  arXiv  Detail & Related papers  (2022-04-11T10:14:35Z)
• TISE: A Toolbox for Text-to-Image Synthesis Evaluation [9.092600296992925]
  We conduct a study on state-of-the-art methods for single- and multi-object text-to-image synthesis. We propose a common framework for evaluating these methods.
  arXiv  Detail & Related papers  (2021-12-02T16:39:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.