# BenthicDINO: Physics-Informed Self-Distillation for View-Invariant Side-Scan Sonar Representations

arXiv: https://arxiv.org/abs/2608.23215 · HTML: https://mlsanity.com/paper/2608.23215/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 23 of 23)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Understanding Dimensional Collapse in Contrastive Self-supervised Learning](https://mlsanity.com/paper/2110.09348/) (2021)
- [Estimating the intrinsic dimension of datasets by a minimal neighborhood information](https://mlsanity.com/paper/1803.06992/) (2018)
- [Self-Supervised Learning with Kernel Dependence Maximization](https://mlsanity.com/paper/2106.08320/) (2021)
- [Machine Learning for Shipwreck Segmentation from Side Scan Sonar Imagery: Dataset and Benchmark](https://mlsanity.com/paper/2401.14546/) (2024)
- [Self-supervised Learning for Sonar Image Classification](https://mlsanity.com/paper/2204.09323/) (2022)
- [A Convolutional Vision Transformer for Semantic Segmentation of Side-Scan Sonar Data](https://mlsanity.com/paper/2302.12416/) (2023)
- [BenthiCat: An opti-acoustic dataset for advancing benthic classification and habitat mapping](https://mlsanity.com/paper/2510.04876/) (2025)
- [Pre-trained Models for Sonar Images](https://mlsanity.com/paper/2108.01111/) (2021)
- [S3Simulator: A benchmarking Side Scan Sonar Simulator dataset for Underwater Image Analysis](https://mlsanity.com/paper/2408.12833/) (2024)
- [Image-to-Height Domain Translation for Synthetic Aperture Sonar](https://mlsanity.com/paper/2112.06307/) (2021)
- [Self-Supervised Learning for Improved Synthetic Aperture Sonar Target Recognition](https://mlsanity.com/paper/2307.15098/) (2023)
- [PhysDNet: Physics-Guided Decomposition Network of Side-Scan Sonar Imagery](https://mlsanity.com/paper/2511.19539/) (2025)
- [Advances in Self-Supervised Learning for Synthetic Aperture Sonar Data Processing, Classification, and Pattern Recognition](https://mlsanity.com/paper/2308.11633/) (2023)
- [On Vision Transformers for Classification Tasks in Side-Scan Sonar Imagery](https://mlsanity.com/paper/2409.12026/) (2024)
- [Self-Supervised Enhancement of Forward-Looking Sonar Images: Bridging Cross-Modal Degradation Gaps through Feature Space Transformation and Multi-Frame Fusion](https://mlsanity.com/paper/2504.10974/) (2025)
- [Mine-JEPA: In-Domain Self-Supervised Learning for Mine-Like Object Classification in Side-Scan Sonar](https://mlsanity.com/paper/2604.00383/) (2026)
- [Physics-informed simulation framework for realistic sonar image generation and statistical validation](https://mlsanity.com/paper/2605.19712/) (2026)

## Abstract (arXiv)

Automated perception in side-scan sonar (SSS) imagery is severely hindered by physical acoustic artifacts, resulting in representations that inextricably mix intrinsic seabed reflectivity with transient viewing geometries. Existing self-supervised learning (SSL) frameworks rely on augmentations designed for natural images, failing to account for acoustic degradation and explicitly enforce view-invariance. To address this gap, we introduce a physics-informed self-distillation framework built upon the DINOv3 architecture utilizing a ConvNeXt-v2-Tiny backbone to maximize data efficiency. The proposed methodology enforces view-invariance through two primary mechanisms: physically motivated augmentations that simulate speckle noise, range-dependent attenuation, and radiometric miscalibration; and a Hilbert-Schmidt Independence Criterion (HSIC) penalty that explicitly decouples learned dense patch features from physical viewing parameters. Furthermore, we propose a dense, hierarchical feature fusion strategy across all four network stages to preserve fine-grained sediment details alongside deep semantic abstractions. Extensive evaluation demonstrates that the framework natively groups complex benthic topographies into stable, noise-free semantic clusters without relying on manual annotations. During supervised downstream tasks on the S3Seg dataset, the fused representations exhibited exceptional data efficiency, achieving 96% of its absolute peak performance using only 10% of the available annotated data, ultimately reaching a mean Intersection over Union (mIoU) of 71.4% and an overall accuracy of 86.5%.