# W-Net: A Deep Model for Fully Unsupervised Image Segmentation

arXiv: https://arxiv.org/abs/1711.08506 · HTML: https://mlsanity.com/paper/1711.08506/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Nov 2017.

## Built on by (most cited first, 30 of 57)

- [Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization](https://mlsanity.com/paper/2205.07839/) (2022)
- [Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression](https://mlsanity.com/paper/2207.05894/) (2022)
- [Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Models](https://mlsanity.com/paper/2105.08127/) (2021)
- [Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion](https://mlsanity.com/paper/2205.07844/) (2022)
- [Unsupervised Foreground Extraction via Deep Region Competition](https://mlsanity.com/paper/2110.15497/) (2021)
- [Neural Compression-Based Feature Learning for Video Restoration](https://mlsanity.com/paper/2203.09208/) (2022)
- [MOVE: Unsupervised Movable Object Segmentation and Detection](https://mlsanity.com/paper/2210.07920/) (2022)
- [SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2310.17874/) (2023)
- [Scribble2D5: Weakly-Supervised Volumetric Image Segmentation via Scribble Annotations](https://mlsanity.com/paper/2205.06779/) (2022)
- [A Spatial Guided Self-supervised Clustering Network for Medical Image Segmentation](https://mlsanity.com/paper/2107.04934/) (2021)
- [SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations](https://mlsanity.com/paper/2403.19507/) (2024)
- [Unsupervised Image Segmentation by Mutual Information Maximization and Adversarial Regularization](https://mlsanity.com/paper/2107.00691/) (2021)
- [Real-time Streaming Video Denoising with Bidirectional Buffers](https://mlsanity.com/paper/2207.06937/) (2022)
- [VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision](https://mlsanity.com/paper/2306.10681/) (2023)
- [GD-VDM: Generated Depth for better Diffusion-based Video Generation](https://mlsanity.com/paper/2306.11173/) (2023)
- [Predicting Mechanically Driven Full-Field Quantities of Interest with Deep Learning-Based Metamodels](https://mlsanity.com/paper/2108.03995/) (2021)
- [On-Device Unsupervised Image Segmentation](https://mlsanity.com/paper/2303.12753/) (2023)
- [DejaVu: Conditional Regenerative Learning to Enhance Dense Prediction](https://mlsanity.com/paper/2303.01573/) (2023)
- [Deep Superpixel Cut for Unsupervised Image Segmentation](https://mlsanity.com/paper/2103.06031/) (2021)
- [Unsupervised Tissue Segmentation via Deep Constrained Gaussian Network](https://mlsanity.com/paper/2208.02912/) (2022)
- [SC-VAE: Sparse Coding-based Variational Autoencoder with Learned ISTA](https://mlsanity.com/paper/2303.16666/) (2023)
- [DynaSeg: A Deep Dynamic Fusion Method for Unsupervised Image Segmentation Incorporating Feature Similarity and Spatial Continuity](https://mlsanity.com/paper/2405.05477/) (2024)
- [An End-to-End Computer Vision Methodology for Quantitative Metallography](https://mlsanity.com/paper/2104.11159/) (2021)
- [Weakly Supervised Volumetric Image Segmentation with Deformed Templates](https://mlsanity.com/paper/2106.03987/) (2021)
- [Towards Bi-directional Skip Connections in Encoder-Decoder Architectures and Beyond](https://mlsanity.com/paper/2203.05709/) (2022)
- [Hybrid Skip: A Biologically Inspired Skip Connection for the UNet Architecture](https://mlsanity.com/paper/2207.04721/) (2022)
- [Segmentation by Factorization: Unsupervised Semantic Segmentation for Pathology by Factorizing Foundation Model Features](https://mlsanity.com/paper/2409.05697/) (2024)
- [CateNorm: Categorical Normalization for Robust Medical Image Segmentation](https://mlsanity.com/paper/2103.15858/) (2021)
- [Pixel-Level Clustering Network for Unsupervised Image Segmentation](https://mlsanity.com/paper/2310.16234/) (2023)
- [Hierarchical-embedding autoencoder with a predictor (HEAP) as efficient architecture for learning long-term evolution of complex multi-scale physical systems](https://mlsanity.com/paper/2505.18857/) (2025)

## Abstract (arXiv)

While significant attention has been recently focused on designing supervised deep semantic segmentation algorithms for vision tasks, there are many domains in which sufficient supervised pixel-level labels are difficult to obtain. In this paper, we revisit the problem of purely unsupervised image segmentation and propose a novel deep architecture for this problem. We borrow recent ideas from supervised semantic segmentation methods, in particular by concatenating two fully convolutional networks together into an autoencoder--one for encoding and one for decoding. The encoding layer produces a k-way pixelwise prediction, and both the reconstruction error of the autoencoder as well as the normalized cut produced by the encoder are jointly minimized during training. When combined with suitable postprocessing involving conditional random field smoothing and hierarchical segmentation, our resulting algorithm achieves impressive results on the benchmark Berkeley Segmentation Data Set, outperforming a number of competing methods.