发现低比特率图像压缩中存在种族偏见，且传统评估方法失效。
Gone With the Bits: Revealing Racial Bias in Low-Rate Neural Compression for Facial Images
- 构建系统框架，通过人脸表型退化检测压缩模型偏见。
- 所有九种模型均现种族偏见，且与重建真实感存在权衡。
- 平衡训练集可减偏但不充分，偏见来自压缩与分类模型双重机制。
神经压缩方法因在极低比特率（低于0.1 bpp）下优于传统方法而日益流行。然而，作为深度学习模型，其训练过程可能引入偏见，导致不同群体个体遭遇不公平结果。本文提出一种通用、结构化、可扩展的框架，用于评估神经图像压缩模型中的偏见。通过该框架分析九种主流模型及其变体，我们首先证明传统失真度量无法捕捉神经压缩中的偏见。其次，发现所有模型均存在种族偏见，可通过重建图像中面部表型退化来检测。进一步分析表明，偏见与解码图像真实感之间存在权衡关系。最后，验证使用种族平衡训练集可降低偏见，但不足以完全消除。偏见源自压缩模型与分类模型双重偏差。本工作为评估与消除神经图像压缩中的偏见迈出关键一步。
原文摘要 · Abstract (English)
Neural compression methods are gaining popularity due to their superior rate-distortion performance over traditional methods, even at extremely low bitrates below 0.1 bpp. As deep learning architectures, these models are prone to bias during the training process, potentially leading to unfair outcomes for individuals in different groups. In this paper, we present a general, structured, scalable framework for evaluating bias in neural image compression models. Using this framework, we investigate racial bias in neural compression algorithms by analyzing nine popular models and their variants. Through this investigation, we first demonstrate that traditional distortion metrics are ineffective in capturing bias in neural compression models. Next, we highlight that racial bias is present in all neural compression models and can be captured by examining facial phenotype degradation in image reconstructions. We then examine the relationship between bias and realism in the decoded images and demonstrate a trade-off across models. Finally, we show that utilizing a racially balanced training set can reduce bias but is not a sufficient bias mitigation strategy. We additionally show the bias can be attributed to compression model bias and classification model bias. We believe that this work is a first step towards evaluating and eliminating bias in neural image compression models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。