# SSeg: Active Sparse Point-Label Augmentation for Semantic Segmentation

arXiv: https://arxiv.org/abs/2510.10163 · HTML: https://mlsanity.com/paper/2510.10163/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 55 references that are in the map.
- First posted on arXiv 11 Oct 2025.

## Builds on (most cited first, 25 of 25)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation](https://mlsanity.com/paper/1911.11789/) (2019)
- [Semantic Segmentation of Underwater Imagery: Dataset and Benchmark](https://mlsanity.com/paper/2004.01241/) (2020)
- [Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset](https://mlsanity.com/paper/1811.01343/) (2018)
- [A Comparative Survey of Deep Active Learning](https://mlsanity.com/paper/2203.13450/) (2022)
- [Superpixel Sampling Networks](https://mlsanity.com/paper/1807.10174/) (2018)
- [SEEDS: Superpixels Extracted via Energy-Driven Sampling](https://mlsanity.com/paper/1309.3848/) (2013)
- [Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.12940/) (2021)
- [A Survey on Deep Active Learning: Recent Advances and New Frontiers](https://mlsanity.com/paper/2405.00334/) (2024)
- [AbdomenAtlas-8K: Annotating 8,000 CT Volumes for Multi-Organ Segmentation in Three Weeks](https://mlsanity.com/paper/2305.09666/) (2023)
- [Denoising Vision Transformers](https://mlsanity.com/paper/2401.02957/) (2024)
- [LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.05570/) (2021)
- [Semantic Segmentation of Remote Sensing Images with Sparse Annotations](https://mlsanity.com/paper/2101.03492/) (2021)
- [SkyScapes -- Fine-Grained Semantic Understanding of Aerial Scenes](https://mlsanity.com/paper/2007.06102/) (2020)
- [Adaptive Superpixel for Active Learning in Semantic Segmentation](https://mlsanity.com/paper/2303.16817/) (2023)
- [Point Label Aware Superpixels for Multi-species Segmentation of Underwater Imagery](https://mlsanity.com/paper/2202.13487/) (2022)
- [Active Learning for Autonomous Intelligent Agents: Exploration, Curiosity, and Interaction](https://mlsanity.com/paper/1403.1497/) (2014)

## Built on by (most cited first, 1 of 1)

- [Leveraging existing sparse point annotations for benthic imagery dense segmentation](https://mlsanity.com/paper/2608.17561/) (2026)

## Abstract (arXiv)

Semantic segmentation is essential for automating remote sensing analysis in fields like ecology. However, fine-grained analysis of complex aerial or underwater imagery remains an open challenge, even for state-of-the-art models. Progress is frequently hindered by the high cost of obtaining the dense, expert-annotated labels required for model supervision. While sparse point-labels are easier to obtain, they introduce challenges regarding which points to annotate and how to propagate the sparse information. We present SSeg, a novel framework that addresses both issues. SSeg first employs an active sampling strategy to guide annotators, maximizing the value of their point labels. Then, it propagates these sparse labels with a hybrid approach leveraging both the best of SAM2 and superpixel-based methods. Experiments on two diverse monitoring datasets demonstrate SSeg's benefits over state-of-the-art approaches. Our main contribution is a simple but effective interactive annotation tool integrating our algorithms. It enables ecology researchers to leverage foundation models and computer vision to efficiently generate high-quality segmentation masks to process their data.