论文标题
量化图像字幕中的社会偏差放大
Quantifying Societal Bias Amplification in Image Captioning
论文作者
论文摘要
我们研究图像字幕中的社会偏见放大。图像字幕模型已被证明可以使性别和种族偏见永存，但是，尚未标准化标题中的社会偏见，以衡量，量化和评估社会偏见。我们提供了有关每个度量标准的优势和局限性的全面研究，并提出了LIC，这是一个研究字幕偏置放大的指标。我们认为，对于图像字幕而言，不足以专注于对受保护属性的正确预测，应考虑整个上下文。我们对传统和最先进的图像字幕模型进行了广泛的评估，令人惊讶的是，仅通过关注受保护的属性预测，偏置缓解模型就会出乎意料地扩大偏见。
We study societal bias amplification in image captioning. Image captioning models have been shown to perpetuate gender and racial biases, however, metrics to measure, quantify, and evaluate the societal bias in captions are not yet standardized. We provide a comprehensive study on the strengths and limitations of each metric, and propose LIC, a metric to study captioning bias amplification. We argue that, for image captioning, it is not enough to focus on the correct prediction of the protected attribute, and the whole context should be taken into account. We conduct extensive evaluation on traditional and state-of-the-art image captioning models, and surprisingly find that, by only focusing on the protected attribute prediction, bias mitigation models are unexpectedly amplifying bias.
