EBA-AI: Ethics-Guided Bias-Aware AI for Efficient Underwater Image Enhancement and Coral Reef Monitoring
It addresses key limitations for marine conservation efforts by improving efficiency, fairness, and interpretability in underwater image processing, though it is incremental as it builds on existing methods like CLIP embeddings and adaptive processing.
This paper tackles the problem of dataset bias, high computational costs, and lack of transparency in AI-based underwater image enhancement for coral reef monitoring by introducing EBA-AI, an ethics-guided bias-aware framework that reduces GPU usage while maintaining competitive enhancement quality, with experiments showing a controlled 1.0 dB drop in PSNR but enabling real-time feasibility.
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/