EBA-AI提升水下图像增强效率与公平性，助力珊瑚礁监测
EBA-AI: Ethics-Guided Bias-Aware AI for Efficient Underwater Image Enhancement and Coral Reef Monitoring
- 用CLIP检测并缓解数据集偏差，确保不同水域环境均衡表现
- 自适应处理降低显存占用，实现实时处理且PSNR仅降1.0 dB
- 融合可解释性与不确定性估计，适合环保机构与科研人员使用
水下图像增强对海洋保护，特别是珊瑚礁监测至关重要。然而，基于AI的增强模型常面临数据偏差、计算成本高和透明度不足的问题，易导致误判。本文提出EBA-AI——一种伦理引导的偏见感知AI框架，利用CLIP嵌入检测并缓解数据偏差，确保在多样水下环境中均衡表征。通过集成自适应处理机制，显著降低GPU使用量，同时保持竞争力的增强质量。在LSUI400、Oceanex和UIEB100数据集上的实验表明，尽管PSNR下降1.0 dB，计算节省仍使大规模海洋监测具备实时可行性。此外，不确定性估计与可解释性技术提升了对AI决策的信任度。与CycleGAN、FunIEGAN、RAUNENet、WaterNet、UGAN、PUGAN和UTUIE对比验证了EBA-AI在效率、公平性与可解释性间的平衡能力。该工作为可持续、偏见感知且计算高效的海洋保护提供了新范式。
原文摘要 · Abstract (English)
Underwater image enhancement is vital for marine conservation, particularly coral reef monitoring. However, AI-based enhancement models often face dataset bias, high computational costs, and lack of transparency, leading to potential misinterpretations. This paper introduces EBA-AI, an ethics-guided bias-aware AI framework to address these challenges. EBA-AI leverages CLIP embeddings to detect and mitigate dataset bias, ensuring balanced representation across varied underwater environments. It also integrates adaptive processing to optimize energy efficiency, significantly reducing GPU usage while maintaining competitive enhancement quality. Experiments on LSUI400, Oceanex, and UIEB100 show that while PSNR drops by a controlled 1.0 dB, computational savings enable real-time feasibility for large-scale marine monitoring. Additionally, uncertainty estimation and explainability techniques enhance trust in AI-driven environmental decisions. Comparisons with CycleGAN, FunIEGAN, RAUNENet, WaterNet, UGAN, PUGAN, and UTUIE validate EBA-AI's effectiveness in balancing efficiency, fairness, and interpretability in underwater image processing. By addressing key limitations of AI-driven enhancement, this work contributes to sustainable, bias-aware, and computationally efficient marine conservation efforts. For interactive visualizations, animations, source code, and access to the preprint, visit: https://lyessaadsaoud.github.io/EBA-AI/
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。