# Investigating Location-Regularised Self-Supervised Feature Learning for Seafloor Visual Imagery

arXiv: https://arxiv.org/abs/2509.06660 · HTML: https://mlsanity.com/paper/2509.06660/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 8 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Self-supervised Learning: Generative or Contrastive](https://mlsanity.com/paper/2006.08218/) (2020)
- [A Survey on Contrastive Self-supervised Learning](https://mlsanity.com/paper/2011.00362/) (2020)
- [Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style](https://mlsanity.com/paper/2106.04619/) (2021)
- [A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends](https://mlsanity.com/paper/2301.05712/) (2023)
- [Unsupervised Learning of Dense Visual Representations](https://mlsanity.com/paper/2011.05499/) (2020)
- [3D CNN-PCA: A Deep-Learning-Based Parameterization for Complex Geomodels](https://mlsanity.com/paper/2007.08478/) (2020)
- [DenseDINO: Boosting Dense Self-Supervised Learning with Token-Based Point-Level Consistency](https://mlsanity.com/paper/2306.04654/) (2023)
- [GeoCLR: Georeference Contrastive Learning for Efficient Seafloor Image Interpretation](https://mlsanity.com/paper/2108.06421/) (2021)

## Built on by (most cited first, 2 of 2)

- [Autonomous Subsea Cable Search and Tracking with Graph-Optimised Priors and Visual Tracking](https://mlsanity.com/paper/2606.23606/) (2026)
- [Remote Awareness of Seafloor Images Collected by AUVs over Low-Bandwidth Communication Links](https://mlsanity.com/paper/2607.18013/) (2026)

## Abstract (arXiv)

High-throughput interpretation of robotically gathered seafloor visual imagery can increase the efficiency of marine monitoring and exploration. Although recent research has suggested that location metadata can enhance self-supervised feature learning (SSL), its benefits across different SSL strategies, models and seafloor image datasets are underexplored. This study evaluates the impact of location-based regularisation on six state-of-the-art SSL frameworks, which include Convolutional Neural Network (CNN) and Vision Transformer (ViT) models with varying latent-space dimensionality. Evaluation across three diverse seafloor image datasets finds that location-regularisation consistently improves downstream classification performance over standard SSL, with average F1-score gains of 4.9 ± 4.0% for CNNs and 6.3 ± 8.9% for ViTs, respectively. While CNNs pretrained on generic datasets benefit from high-dimensional latent representations, dataset-optimised SSL achieves similar performance across the high (512) and low (128) dimensional latent representations. Location-regularised SSL improves CNN performance over pre-trained models by 2.7 ± 2.7% and 10.1 ± 9.4% for high and low-dimensional latent representations, respectively. For ViTs, high-dimensionality benefits both pre-trained and dataset-optimised SSL. Although location-regularisation improves SSL performance compared to standard SSL methods, pre-trained ViTs show strong generalisation, matching the best-performing location-regularised SSL with F1-scores of 0.795 ± 0.075 and 0.795 ± 0.077, respectively. The findings highlight the value of location metadata for SSL regularisation, particularly when using low-dimensional latent representations, and demonstrate strong generalisation of high-dimensional ViTs for seafloor image analysis.