让声呐模型学会忘记海底特征，提升泛化能力与可解释性。
Supervised Contrastive Machine Unlearning of Background Bias in Sonar Image Classification with Fine-Grained Explainable AI
- 用对比学习机制主动消除模型对海底背景的依赖。
- 在真实与合成数据上显著提升去偏效果与模型鲁棒性。
- 结合可视化解释工具，清晰展示模型遗忘过程，适合安全敏感场景使用。
声呐图像分析在民用与国防领域中对目标检测与分类至关重要。尽管存在真实与合成数据集，现有高精度AI模型常过度依赖海底特征，导致泛化能力差。为此，我们提出一个新框架，包含两个关键模块：(i) 靶向对比去偏（TCU）模块，将传统三元组损失扩展为减少海底背景偏差、提升泛化能力；(ii) 去偏可解释框架（UESF），通过适配LIME解释器生成更准确、局部化的归因，直观呈现模型主动遗忘的内容。在真实与合成声呐数据集上的大量实验验证了该方法的有效性，显著提升了去偏性能、模型鲁棒性与可解释性。
原文摘要 · Abstract (English)
Acoustic sonar image analysis plays a critical role in object detection and classification, with applications in both civilian and defense domains. Despite the availability of real and synthetic datasets, existing AI models that achieve high accuracy often over-rely on seafloor features, leading to poor generalization. To mitigate this issue, we propose a novel framework that integrates two key modules: (i) a Targeted Contrastive Unlearning (TCU) module, which extends the traditional triplet loss to reduce seafloor-induced background bias and improve generalization, and (ii) the Unlearn to Explain Sonar Framework (UESF), which provides visual insights into what the model has deliberately forgotten while adapting the LIME explainer to generate more faithful and localized attributions for unlearning evaluation. Extensive experiments across both real and synthetic sonar datasets validate our approach, demonstrating significant improvements in unlearning effectiveness, model robustness, and interpretability.
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。