由非残障人士训练的模型：评估图像质量如何影响产品描述生成
"It's trained by non-disabled people": Evaluating How Image Quality Affects Product Captioning with Vision-Language Models
AI总结：
研究评估图像质量对视觉语言模型生成产品描述准确性的影响，发现图像质量下降会导致模型性能显著降低，提出改进模型可靠性的建议。
摘要：
视觉语言模型（VLMs）越来越多地被盲人和低视力（BLV）人士用于识别和理解日常生活中的产品，如食品、个人护理用品和家居用品。尽管其普及率高，但我们缺乏对常见图像质量问题（如模糊、构图错误和旋转）如何影响VLM生成的描述准确性以及这些描述是否满足BLV人士信息需求的实证理解。基于对86名BLV参与者调查，我们开发了一个包含1,859个产品图像的标注数据集，系统评估图像质量问题对VLM生成描述的影响。尽管最佳VLM在无质量问题的图像上达到98%的准确率，但存在质量问题时准确率降至75%，问题叠加时情况进一步恶化。我们讨论了在整个过程中以残障人士经验为中心的模型评估的必要性，并为人机交互（HCI）和机器学习（ML）研究人员提供具体建议，以使VLM更可靠地服务于BLV人士。
英文摘要：
Vision-Language Models (VLMs) are increasingly used by blind and low-vision (BLV) people to identify and understand products in their everyday lives, such as food, personal care items, and household goods. Despite their prevalence, we lack an empirical understanding of how common image quality issues--such as blur, misframing, and rotation--affect the accuracy of VLM-generated captions and whether the resulting captions meet BLV people's information needs. Based on a survey of 86 BLV participants, we develop an annotated dataset of 1,859 product images from BLV people to systematically evaluate how image quality issues affect VLM-generated captions. While the best VLM achieves 98% accuracy on images with no quality issues, accuracy drops to 75% overall when quality issues are present, worsening considerably as issues compound. We discuss the need for model evaluations that center on disabled people's experiences throughout the process and offer concrete recommendations for HCI and ML researchers to make VLMs more reliable for BLV people.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
