EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models

• URL: http://arxiv.org/abs/2406.16562v3
• Date: Thu, 10 Oct 2024 14:04:07 GMT
• Title: EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models
• Authors: Zhiyu Tan, Xiaomeng Yang, Luozheng Qin, Mengping Yang, Cheng Zhang, Hao Li,
• Abstract summary: We propose EvalAlign, a metric characterized by its accuracy, stability, and fine granularity. We develop evaluation protocols that focus on two key dimensions: image faithfulness and text-image alignment. EvalAlign aligns more closely with human preferences than existing metrics, confirming its effectiveness and utility in model assessment.
• Score: 16.18275805302776
• License:
• Abstract: The recent advancements in text-to-image generative models have been remarkable. Yet, the field suffers from a lack of evaluation metrics that accurately reflect the performance of these models, particularly lacking fine-grained metrics that can guide the optimization of the models. In this paper, we propose EvalAlign, a metric characterized by its accuracy, stability, and fine granularity. Our approach leverages the capabilities of Multimodal Large Language Models (MLLMs) pre-trained on extensive data. We develop evaluation protocols that focus on two key dimensions: image faithfulness and text-image alignment. Each protocol comprises a set of detailed, fine-grained instructions linked to specific scoring options, enabling precise manual scoring of the generated images. We supervised fine-tune (SFT) the MLLM to align with human evaluative judgments, resulting in a robust evaluation model. Our evaluation across 24 text-to-image generation models demonstrate that EvalAlign not only provides superior metric stability but also aligns more closely with human preferences than existing metrics, confirming its effectiveness and utility in model assessment.

Related papers

• VHELM: A Holistic Evaluation of Vision Language Models [75.88987277686914]
  We present the Holistic Evaluation of Vision Language Models (VHELM) VHELM aggregates various datasets to cover one or more of the 9 aspects: visual perception, knowledge, reasoning, bias, fairness, multilinguality, robustness, toxicity, and safety. Our framework is designed to be lightweight and automatic so that evaluation runs are cheap and fast.
  arXiv  Detail & Related papers  (2024-10-09T17:46:34Z)
• Opinion-Unaware Blind Image Quality Assessment using Multi-Scale Deep Feature Statistics [54.08757792080732]
  We propose integrating deep features from pre-trained visual models with a statistical analysis model to achieve opinion-unaware BIQA (OU-BIQA) Our proposed model exhibits superior consistency with human visual perception compared to state-of-the-art BIQA models.
  arXiv  Detail & Related papers  (2024-05-29T06:09:34Z)
• Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models [85.96013373385057]
  Fine-tuning text-to-image models with reward functions trained on human feedback data has proven effective for aligning model behavior with human intent. However, excessive optimization with such reward models, which serve as mere proxy objectives, can compromise the performance of fine-tuned models. We propose TextNorm, a method that enhances alignment based on a measure of reward model confidence estimated across a set of semantically contrastive text prompts.
  arXiv  Detail & Related papers  (2024-04-02T11:40:38Z)
• QualEval: Qualitative Evaluation for Model Improvement [82.73561470966658]
  We propose QualEval, which augments quantitative scalar metrics with automated qualitative evaluation as a vehicle for model improvement. QualEval uses a powerful LLM reasoner and our novel flexible linear programming solver to generate human-readable insights. We demonstrate that leveraging its insights, for example, improves the absolute performance of the Llama 2 model by up to 15% points relative.
  arXiv  Detail & Related papers  (2023-11-06T00:21:44Z)
• EvalCrafter: Benchmarking and Evaluating Large Video Generation Models [70.19437817951673]
  We argue that it is hard to judge the large conditional generative models from the simple metrics since these models are often trained on very large datasets with multi-aspect abilities. Our approach involves generating a diverse and comprehensive list of 700 prompts for text-to-video generation. Then, we evaluate the state-of-the-art video generative models on our carefully designed benchmark, in terms of visual qualities, content qualities, motion qualities, and text-video alignment with 17 well-selected objective metrics.
  arXiv  Detail & Related papers  (2023-10-17T17:50:46Z)
• Evaluating Representations with Readout Model Switching [19.907607374144167]
  In this paper, we propose to use the Minimum Description Length (MDL) principle to devise an evaluation metric. We design a hybrid discrete and continuous-valued model space for the readout models and employ a switching strategy to combine their predictions. The proposed metric can be efficiently computed with an online method and we present results for pre-trained vision encoders of various architectures.
  arXiv  Detail & Related papers  (2023-02-19T14:08:01Z)
• Effective Robustness against Natural Distribution Shifts for Models with Different Training Data [113.21868839569]
  "Effective robustness" measures the extra out-of-distribution robustness beyond what can be predicted from the in-distribution (ID) performance. We propose a new evaluation metric to evaluate and compare the effective robustness of models trained on different data.
  arXiv  Detail & Related papers  (2023-02-02T19:28:41Z)
• Who Explains the Explanation? Quantitatively Assessing Feature Attribution Methods [0.0]
  We propose a novel evaluation metric -- the Focus -- designed to quantify the faithfulness of explanations. We show the robustness of the metric through randomization experiments, and then use Focus to evaluate and compare three popular explainability techniques. Our results find LRP and GradCAM to be consistent and reliable, while the latter remains most competitive even when applied to poorly performing models.
  arXiv  Detail & Related papers  (2021-09-28T07:10:24Z)

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.