On the performance of machine learning fairness in image classification
On the performance of machine learning fairness in image classification
复制标题
DOI：
10.1117/12.2665725
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Utsab Khakurel;D. Rawat
中科院分区：
文献类型：
--
作者：
Utsab Khakurel;D. Rawat
近年来，计算机视觉在使机器能够执行从图像分类和分割到图像生成和视频分析等广泛任务方面取得了重大进展。这是一个快速发展的领域，旨在使机器能够解释和理解来自环境的视觉信息。计算机视觉中的一个关键任务是图像分类，其中算法根据图像中的对象的视觉特征对其进行识别和分类。图像分类具有广泛的应用，从图像搜索和推荐系统到自动驾驶和医疗诊断。然而，最近的研究强调了图像分类算法中存在的偏见，特别是对于人类敏感的属性，如性别，种族和民族。一些例子是，与女性相比，计算机程序员在图像中的男性背景下被预测得更好，并且与彩色图像相比，该算法在灰度图像上的准确性更好。这种识别对象的差异是通过相关性发展起来的，算法从上下文中的对象中学习，称为上下文偏见。这种偏见可能导致不准确的决策，在招聘，医疗保健和安全等领域产生潜在后果。在本文中，我们进行了一项实证研究，通过转移学习使用深度卷积神经网络（CNN）来研究基于敏感属性性别的图像分类域中的偏差，并使用数据增强来最大限度地减少图像上下文中的偏差，以提高整体模型性能。此外，进行跨数据泛化实验，以评估模型在流行的开源图像数据集上的鲁棒性。
In recent years, computer vision has made significant strides in enabling machines to perform a wide range of tasks, from image classification and segmentation to image generation and video analysis. It is a rapidly evolving field that aims to enable machines to interpret and understand visual information from the environment. One key task in computer vision is image classification, where algorithms identify and categorize objects in images based on their visual features. Image classification has a wide range of applications, from image search and recommendation systems to autonomous driving and medical diagnosis. However, recent research has highlighted the presence of bias in image classification algorithms, particularly with respect to human-sensitive attributes such as gender, race, and ethnicity. Some examples are computer programmers being predicted better in the context of men in images compared to women, and the accuracy of the algorithm being better on greyscale images compared to colored images. This discrepancy in identifying objects is developed through correlation the algorithm learns from the objects in context known as contextual bias. This bias can result in inaccurate decisions, with potential consequences in areas such as hiring, healthcare, and security. In this paper, we conduct an empirical study to investigate bias in the image classification domain based on sensitive attribute gender using deep convolutional neural networks (CNN) through transfer learning and minimize bias within the image context using data augmentation to improve overall model performance. In addition, cross-data generalization experiments are conducted to evaluate model robustness across popular open-source image datasets.