用动态修复+自适应阈值，让图像识别更公平且不需重训练。
FAIR-SIGHT: Fairness Assurance in Image Recognition via Simultaneous Conformal Thresholding and Dynamic Output Repair
- 通过非一致性分数同时衡量预测误差和公平性问题。
- 在多个数据集上显著降低群体与个体公平性差异，保持高精度。
- 无需模型参数或重新训练，适合部署于已有视觉系统中。
我们提出 FAIR-SIGHT，一种创新的后处理框架，通过结合共形预测与动态输出修复机制，确保计算机视觉系统的公平性。该方法设计了一种兼顾预测误差与公平性违规的公平感知非一致性分数，利用共形预测建立自适应阈值，提供严格有限样本、分布无关的保证。当新图像的非一致性分数超过校准阈值时，FAIR-SIGHT 会实施针对性修正，如分类任务中的对数几率偏移、检测任务中的置信度重校准，以减少群体与个体公平性差异，且无需重训练或访问内部模型参数。理论分析验证了方法的误差控制与收敛性；大量实证评估表明，该框架在多个基准数据集上有效降低公平性差距，同时保持高预测性能。
原文摘要 · Abstract (English)
We introduce FAIR-SIGHT, an innovative post-hoc framework designed to ensure fairness in computer vision systems by combining conformal prediction with a dynamic output repair mechanism. Our approach calculates a fairness-aware non-conformity score that simultaneously assesses prediction errors and fairness violations. Using conformal prediction, we establish an adaptive threshold that provides rigorous finite-sample, distribution-free guarantees. When the non-conformity score for a new image exceeds the calibrated threshold, FAIR-SIGHT implements targeted corrective adjustments, such as logit shifts for classification and confidence recalibration for detection, to reduce both group and individual fairness disparities, all without the need for retraining or having access to internal model parameters. Comprehensive theoretical analysis validates our method's error control and convergence properties. At the same time, extensive empirical evaluations on benchmark datasets show that FAIR-SIGHT significantly reduces fairness disparities while preserving high predictive performance.
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。