# W-Net: A Deep Model for Fully Unsupervised Image Segmentation Source: [W-Net: A Deep Model for Fully Unsupervised Image Segmentation]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:50:10.530Z Authors: Xide Xia, Brian Kulis Published: 2017-11-22T21:06:13.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Unsupervised Object Segmentation on CUB](): Unsupervised Object Segmentation; CUB; Jaccard Index: 24.8. ## Original sources and implementation [Original paper]() [PDF]()