# On-Device Unsupervised Image Segmentation

arXiv: https://arxiv.org/abs/2303.12753 · HTML: https://mlsanity.com/paper/2303.12753/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 44 references that are in the map.
- First posted on arXiv 24 Feb 2023.

## Builds on (most cited first, 21 of 21)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Image Segmentation Using Deep Learning: A Survey](https://mlsanity.com/paper/2001.05566/) (2020)
- [Learning Deconvolution Network for Semantic Segmentation](https://mlsanity.com/paper/1505.04366/) (2015)
- [Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation](https://mlsanity.com/paper/1901.02985/) (2019)
- [On-Device Training Under 256KB Memory](https://mlsanity.com/paper/2206.15472/) (2022)
- [On-Device Machine Learning: An Algorithms and Learning Theory Perspective](https://mlsanity.com/paper/1911.00623/) (2019)
- [Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering](https://mlsanity.com/paper/2007.09990/) (2020)
- [Classification using Hyperdimensional Computing: A Review](https://mlsanity.com/paper/2004.11204/) (2020)
- [W-Net: A Deep Model for Fully Unsupervised Image Segmentation](https://mlsanity.com/paper/1711.08506/) (2017)
- [Labels4Free: Unsupervised Segmentation using StyleGAN](https://mlsanity.com/paper/2103.14968/) (2021)
- [Hardware/Software Co-Exploration of Neural Architectures](https://mlsanity.com/paper/1907.04650/) (2019)
- [Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Tasks](https://mlsanity.com/paper/2002.04116/) (2020)
- [Accuracy vs. Efficiency: Achieving Both through FPGA-Implementation Aware Neural Architecture Search](https://mlsanity.com/paper/1901.11211/) (2019)
- [Federated Contrastive Learning for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/2204.10983/) (2022)
- [Standing on the Shoulders of Giants: Hardware and Neural Architecture Co-Search with Hot Start](https://mlsanity.com/paper/2007.09087/) (2020)
- [The Larger The Fairer? Small Neural Networks Can Achieve Fairness for Edge Devices](https://mlsanity.com/paper/2202.11317/) (2022)
- [Achieving Super-Linear Speedup across Multi-FPGA for Real-Time DNN Inference](https://mlsanity.com/paper/1907.08985/) (2019)
- [Automated Architecture Search for Brain-inspired Hyperdimensional Computing](https://mlsanity.com/paper/2202.05827/) (2022)

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

- [Muffin: A Framework Toward Multi-Dimension AI Fairness by Uniting Off-the-Shelf Models](https://mlsanity.com/paper/2308.13730/) (2023)
- [Towards On-device Learning on the Edge: Ways to Select Neurons to Update under a Budget Constraint](https://mlsanity.com/paper/2312.05282/) (2023)
- [Activation Map Compression through Tensor Decomposition for Deep Learning](https://mlsanity.com/paper/2411.06346/) (2024)
- [A Physics-guided Generative AI Toolkit for Geophysical Monitoring](https://mlsanity.com/paper/2401.03131/) (2024)
- [Study of Training Dynamics for Memory-Constrained Fine-Tuning](https://mlsanity.com/paper/2510.19675/) (2025)
- [CiliaGraph: Enabling Expression-enhanced Hyper-Dimensional Computation in Ultra-Lightweight and One-Shot Graph Classification on Edge](https://mlsanity.com/paper/2405.19033/) (2024)
- [Computational Performance Bounds Prediction in Quantum Computing with Unstable Noise](https://mlsanity.com/paper/2507.17043/) (2025)
- [Memory Constrained Dynamic Subnetwork Update for Transfer Learning](https://mlsanity.com/paper/2510.20979/) (2025)
- [Two Teachers Better Than One: Hardware-Physics Co-Guided Distributed Scientific Machine Learning](https://mlsanity.com/paper/2603.09032/) (2026)
- [FaceParts: Segmentation and Editing of Gaussian Splatting](https://mlsanity.com/paper/2605.13853/) (2026)

## Abstract (arXiv)

Along with the breakthrough of convolutional neural networks, learning-based segmentation has emerged in many research works. Most of them are based on supervised learning, requiring plenty of annotated data; however, to support segmentation, a label for each pixel is required, which is obviously expensive. As a result, the issue of lacking annotated segmentation data commonly exists. Continuous learning is a promising way to deal with this issue; however, it still has high demands on human labor for annotation. What's more, privacy is highly required in segmentation data for real-world applications, which further calls for on-device learning. In this paper, we aim to resolve the above issue in an alternative way: Instead of supervised segmentation, we propose to develop efficient unsupervised segmentation that can be executed on edge devices. Based on our observation that segmentation can obtain high performance when pixels are mapped to a high-dimension space, we for the first time bring brain-inspired hyperdimensional computing (HDC) to the segmentation task. We build the HDC-based unsupervised segmentation framework, namely "SegHDC". In SegHDC, we devise a novel encoding approach that follows the Manhattan distance. A clustering algorithm is further developed on top of the encoded high-dimension vectors to obtain segmentation results. Experimental results show SegHDC can significantly surpass neural network-based unsupervised segmentation. On a standard segmentation dataset, DSB2018, SegHDC can achieve a 28.0% improvement in Intersection over Union (IoU) score; meanwhile, it achieves over 300x speedup on Raspberry PI. What's more, for a larger size image in the BBBC005 dataset, the existing approach cannot be accommodated to Raspberry PI due to out of memory; on the other hand, SegHDC can obtain segmentation results within 3 minutes while achieving a 0.9587 IoU score.