视觉-语言模型和生成图像模型中的偏见检测与旋转鲁棒性缓解
Bias Detection and Rotation-Robustness Mitigation in Vision-Language Models and Generative Image Models
AI总结：
本文提出旋转鲁棒缓解策略，通过数据增强、表征对齐和模型正则化，提升视觉-语言和生成图像模型在旋转和分布偏移下的鲁棒性和公平性。
摘要：
视觉-语言模型（VLMs）和生成图像模型在多模态任务中取得了显著性能，但其在输入变换下的鲁棒性和公平性仍不够充分。本研究探讨了当前最先进的视觉-语言和生成模型中的偏见传播和鲁棒性退化问题，特别关注图像旋转和分布偏移。我们分析了旋转引起的扰动如何影响模型预测、置信度校准和人口偏见模式。为了解决这些问题，我们提出了结合数据增强、表征对齐和模型级正则化的旋转鲁棒缓解策略。在多个数据集上的实验结果表明，所提出的方法显著提高了鲁棒性，同时减少了偏见放大，而不会牺牲整体性能。本研究突显了当前多模态系统的关键限制，并为构建更可靠和公平的AI模型提供了实用的缓解技术。
英文摘要：
Vision-Language Models (VLMs) and generative image models have achieved remarkable performance across multimodal tasks, yet their robustness and fairness under input transformations remain insufficiently explored. This work investigates bias propagation and robustness degradation in state-of-the-art vision-language and generative models, with a particular focus on image rotation and distributional shifts. We analyze how rotation-induced perturbations affect model predictions, confidence calibration, and demographic bias patterns. To address these issues, we propose rotation-robust mitigation strategies that combine data augmentation, representation alignment, and model-level regularization. Experimental results across multiple datasets demonstrate that the proposed methods significantly improve robustness while reducing bias amplification without sacrificing overall performance. This study highlights critical limitations of current multimodal systems and provides practical mitigation techniques for building more reliable and fair AI models.
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。
