Centre for Alcohol Policy Research, La Trobe University, Melbourne, Victoria, Australia.
Department of Computer Science and Information Technology, La Trobe University, Melbourne, Victoria, Australia.
Alcohol Clin Exp Res. 2022 Oct;46(10):1837-1845. doi: 10.1111/acer.14925. Epub 2022 Oct 15.
Seeing alcohol in media has been demonstrated to increase alcohol craving, impulsive decision-making, and hazardous drinking. Due to the exponential growth of (social) media use it is important to develop algorithms to quantify alcohol exposure efficiently in electronic images. In this article, we describe the development of an improved version of the Alcoholic Beverage Identification Deep Learning Algorithm (ABIDLA), called ABIDLA2.
ABIDLA2 was trained on 191,286 images downloaded from Google Image Search results (based on search terms) and Bing Image Search results. In Task-1, ABIDLA2 identified images as containing one of eight beverage categories (beer/cider cup, beer/cider bottle, beer/cider can, wine, champagne, cocktails, whiskey/cognac/brandy, other images). In Task-2, ABIDLA2 made a binary classification between images containing an "alcoholic beverage" or "other". An ablation study was performed to determine which techniques improved algorithm performance.
ABIDLA2 was most accurate in identifying Whiskey/Cognac/Brandy (88.1%) followed by Beer/Cider Can (80.5%), Beer/Cider Bottle (78.3%), and Wine (77.8%). Its overall accuracy was 77.0% (Task-1) and 87.7% (Task-2). Even the identification of the least accurate beverage category (Champagne, 64.5%) was more than five times higher than random chance (12.5% = 1/8 categories). The implementation of balanced data sampler to address class skewness and the use of self-training to make use of a large, secondary, weakly labeled dataset particularly improved overall algorithm performance.
With extended capabilities and a higher accuracy, ABIDLA2 outperforms its predecessor and enables the screening of any kind of electronic media rapidly to estimate the quantity of alcohol exposure. Quantifying alcohol exposure automatically through algorithms like ABIDLA2 is important because viewing images of alcoholic beverages in media tends to increase alcohol consumption and related harms.
研究表明，媒体中的酒精形象会增加饮酒欲望、冲动决策和危险饮酒行为。由于社交媒体的使用呈指数级增长，因此开发有效的算法来量化电子图像中的酒精暴露量非常重要。本文描述了一种改进的酒精饮料识别深度学习算法（ABIDLA）的开发，称为 ABIDLA2。
ABIDLA2 是在从谷歌图片搜索结果（基于搜索词）和必应图片搜索结果中下载的 191,286 张图像上进行训练的。在任务 1 中，ABIDLA2 识别出包含八种饮料类别之一的图像（啤酒/苹果酒杯、啤酒/苹果酒瓶、啤酒/苹果酒罐、葡萄酒、香槟、鸡尾酒、威士忌/白兰地、其他图像）。在任务 2 中，ABIDLA2 对包含“酒精饮料”或“其他”的图像进行二进制分类。进行了一项消融研究，以确定哪些技术提高了算法性能。
ABIDLA2 对威士忌/白兰地的识别最为准确（88.1%），其次是啤酒/苹果酒罐（80.5%）、啤酒/苹果酒瓶（78.3%）和葡萄酒（77.8%）。其总体准确率为 77.0%（任务 1）和 87.7%（任务 2）。即使是识别准确率最低的饮料类别（香槟，64.5%）也高于随机概率（12.5%=1/8 个类别）的五倍以上。实现平衡数据采样器来解决类别偏斜问题，以及使用自我训练来利用大型、次要的、弱标记数据集，特别提高了整体算法性能。
ABIDLA2 具有扩展功能和更高的准确性，优于其前身，能够快速筛选任何类型的电子媒体，估计酒精暴露量。通过 ABIDLA2 等算法自动量化酒精暴露量很重要，因为媒体中观看酒精饮料的图像往往会增加饮酒量和相关危害。
