# Supervised Contrastive Machine Unlearning of Background Bias in Sonar Image Classification with Fine-Grained Explainable AI

arXiv: https://arxiv.org/abs/2512.01291 · HTML: https://mlsanity.com/paper/2512.01291/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 1 Dec 2025.

## Builds on (most cited first, 12 of 12)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation](https://mlsanity.com/paper/2010.16061/) (2020)
- [A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI](https://mlsanity.com/paper/1907.07374/) (2019)
- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects](https://mlsanity.com/paper/2403.08254/) (2024)
- [A Review on Machine Unlearning](https://mlsanity.com/paper/2411.11315/) (2024)
- [Contrastive Unlearning: A Contrastive Approach to Machine Unlearning](https://mlsanity.com/paper/2401.10458/) (2024)
- [Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis](https://mlsanity.com/paper/2501.09333/) (2025)
- [S3Simulator: A benchmarking Side Scan Sonar Simulator dataset for Underwater Image Analysis](https://mlsanity.com/paper/2408.12833/) (2024)
- [Syn2Real Domain Generalization for Underwater Mine-like Object Detection Using Side-Scan Sonar](https://mlsanity.com/paper/2410.12953/) (2024)
- [A Novel Context-Adaptive Fusion of Shadow and Highlight Regions for Efficient Sonar Image Classification](https://mlsanity.com/paper/2506.01445/) (2025)

## Abstract (arXiv)

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.