# Point Label Aware Superpixels for Multi-species Segmentation of Underwater Imagery

arXiv: https://arxiv.org/abs/2202.13487 · HTML: https://mlsanity.com/paper/2202.13487/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 49 references that are in the map.
- First posted on arXiv 27 Feb 2022.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [What's the Point: Semantic Segmentation with Point Supervision](https://mlsanity.com/paper/1506.02106/) (2015)
- [Learning random-walk label propagation for weakly-supervised semantic segmentation](https://mlsanity.com/paper/1802.00470/) (2018)
- [Superpixel Sampling Networks](https://mlsanity.com/paper/1807.10174/) (2018)
- [SEEDS: Superpixels Extracted via Energy-Driven Sampling](https://mlsanity.com/paper/1309.3848/) (2013)
- [Semantic Segmentation of Remote Sensing Images with Sparse Annotations](https://mlsanity.com/paper/2101.03492/) (2021)
- [Towards Highly Accurate Coral Texture Images Classification Using Deep Convolutional Neural Networks and Data Augmentation](https://mlsanity.com/paper/1804.00516/) (2018)
- [Multi-species Seagrass Detection and Classification from Underwater Images](https://mlsanity.com/paper/2009.09924/) (2020)
- [Towards Adaptive Benthic Habitat Mapping](https://mlsanity.com/paper/2006.11453/) (2020)

## Built on by (most cited first, 10 of 10)

- [The Coralscapes Dataset: Semantic Scene Understanding in Coral Reefs](https://mlsanity.com/paper/2503.20000/) (2025)
- [Image Labels Are All You Need for Coarse Seagrass Segmentation](https://mlsanity.com/paper/2303.00973/) (2023)
- [CoralSCOP-LAT: Labeling and Analyzing Tool for Coral Reef Images with Dense Mask](https://mlsanity.com/paper/2410.20436/) (2024)
- [AI-Driven Marine Robotics: Emerging Trends in Underwater Perception and Ecosystem Monitoring](https://mlsanity.com/paper/2509.01878/) (2025)
- [AI-driven Dispensing of Coral Reseeding Devices for Broad-scale Restoration of the Great Barrier Reef](https://mlsanity.com/paper/2509.01019/) (2025)
- [A drone-based framework for coral habitat mapping via weakly supervised segmentation](https://mlsanity.com/paper/2508.18958/) (2025)
- [SSeg: Active Sparse Point-Label Augmentation for Semantic Segmentation](https://mlsanity.com/paper/2510.10163/) (2025)
- [Human-in-the-Loop Segmentation of Multi-species Coral Imagery](https://mlsanity.com/paper/2404.09406/) (2024)
- [Long-Term Multi-Session 3D Reconstruction Under Substantial Appearance Change](https://mlsanity.com/paper/2602.20584/) (2026)
- [Leveraging existing sparse point annotations for benthic imagery dense segmentation](https://mlsanity.com/paper/2608.17561/) (2026)

## Abstract (arXiv)

Monitoring coral reefs using underwater vehicles increases the range of marine surveys and availability of historical ecological data by collecting significant quantities of images. Analysis of this imagery can be automated using a model trained to perform semantic segmentation, however it is too costly and time-consuming to densely label images for training supervised models. In this letter, we leverage photo-quadrat imagery labeled by ecologists with sparse point labels. We propose a point label aware method for propagating labels within superpixel regions to obtain augmented ground truth for training a semantic segmentation model. Our point label aware superpixel method utilizes the sparse point labels, and clusters pixels using learned features to accurately generate single-species segments in cluttered, complex coral images. Our method outperforms prior methods on the UCSD Mosaics dataset by 3.62% for pixel accuracy and 8.35% for mean IoU for the label propagation task, while reducing computation time reported by previous approaches by 76%. We train a DeepLabv3+ architecture and outperform state-of-the-art for semantic segmentation by 2.91% for pixel accuracy and 9.65% for mean IoU on the UCSD Mosaics dataset and by 4.19% for pixel accuracy and 14.32% mean IoU for the Eilat dataset.