模型无关的性别去偏图像描述生成
Model-Agnostic Gender Debiased Image Captioning
AI总结：
针对图像描述模型中的性别偏见，提出模型无关的LIBRA框架，通过合成偏置样本学习，同时纠正性别误分类和减少刻板词语生成。
摘要：
图像描述生成模型已知会延续并放大训练集中的有害社会偏见。在本工作中，我们旨在减轻图像描述生成模型中的此类性别偏见。虽然先前的工作通过强制模型关注人物来减少性别误分类，但这样做反而以牺牲正确性别预测为代价，生成了性别刻板印象的词语。基于这一观察，我们假设影响图像描述生成模型的性别偏见有两种类型：1) 利用上下文来预测性别的偏见；2) 由于性别而导致生成某些（通常是刻板印象的）词语的概率偏见。为了减轻这两种类型的性别偏见，我们提出了一个名为LIBRA的框架，该框架从合成偏见的样本中学习，以减少这两种偏见，纠正性别误分类并将性别刻板印象的词语改为更中性的词语。代码可在 https://github.com/rebnej/LIBRA 获取。
英文摘要：
Image captioning models are known to perpetuate and amplify harmful societal bias in the training set. In this work, we aim to mitigate such gender bias in image captioning models. While prior work has addressed this problem by forcing models to focus on people to reduce gender misclassification, it conversely generates gender-stereotypical words at the expense of predicting the correct gender. From this observation, we hypothesize that there are two types of gender bias affecting image captioning models: 1) bias that exploits context to predict gender, and 2) bias in the probability of generating certain (often stereotypical) words because of gender. To mitigate both types of gender biases, we propose a framework, called LIBRA, that learns from synthetically biased samples to decrease both types of biases, correcting gender misclassification and changing gender-stereotypical words to more neutral ones. Code is available at https://github.com/rebnej/LIBRA.
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。
