arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.01854cs.CV
收藏

自监督学习视觉模型中社会偏见分布的研究

A study on the distribution of social biases in self-supervised learning visual models

Universidad Autónoma de Madrid(马德里自治大学)

Kirill Sirotkin, Pablo Carballeira, Marcos Escudero-Viñolo

摘要:

深度神经网络在学习数据分布方面是有效的,如果它被充分采样的话。然而,它们可能被隐含地包含在训练数据中的非相关因素强烈地偏置。这些包括操作偏差,例如无效或不均匀的数据采样,但也包括道德问题,因为社会偏差隐含地存在于\textemdash中,即使是无意的,在训练数据中或在不公平的训练计划中明确定义。在影响人类进程的任务中,学习社会偏见可能会产生歧视性、不道德和不可信的后果。人们通常认为社会偏见源于对标记数据的监督学习,因此,自监督学习(SSL)错误地表现为一种有效和无偏见的解决方案,因为它不需要标记数据。然而,最近证明,一种流行的SSL方法也包含偏差。在本文中,我们研究了一组不同的SSL视觉模型的偏差,这些模型使用ImageNet数据进行训练,使用心理学专家设计的方法和数据集来测量社会偏见。我们发现,SSL模型的类型和它所包含的偏见的数量之间存在相关性。此外,结果还表明,这个数字并不严格取决于模型的准确性和整个网络的变化。最后,我们得出结论,谨慎的SSL模型选择过程可以减少部署模型中的社会偏见数量,同时保持高性能。

英文摘要:

Deep neural networks are efficient at learning the data distribution if it is sufficiently sampled. However, they can be strongly biased by non-relevant factors implicitly incorporated in the training data. These include operational biases, such as ineffective or uneven data sampling, but also ethical concerns, as the social biases are implicitly present\textemdash even inadvertently, in the training data or explicitly defined in unfair training schedules. In tasks having impact on human processes, the learning of social biases may produce discriminatory, unethical and untrustworthy consequences. It is often assumed that social biases stem from supervised learning on labelled data, and thus, Self-Supervised Learning (SSL) wrongly appears as an efficient and bias-free solution, as it does not require labelled data. However, it was recently proven that a popular SSL method also incorporates biases. In this paper, we study the biases of a varied set of SSL visual models, trained using ImageNet data, using a method and dataset designed by psychological experts to measure social biases. We show that there is a correlation between the type of the SSL model and the number of biases that it incorporates. Furthermore, the results also suggest that this number does not strictly depend on the model's accuracy and changes throughout the network. Finally, we conclude that a careful SSL model selection process can reduce the number of social biases in the deployed model, whilst keeping high performance.

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。

↑