W-Net: A Deep Model for Fully Unsupervised Image Segmentation
Preprint
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.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Xception: Deep Learning with Depthwise Separable Convolutions2017
- The Pascal Visual Object Classes Challenge: A RetrospectiveInternational Journal of Computer Vision, 2014
- Learning Hierarchical Features for Scene LabelingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Contour Detection and Hierarchical Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- A Variational Framework for Multiregion Pairwise-Similarity-Based Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition2007
- Hierarchy and adaptivity in segmenting visual scenesNature, 2006
- Efficient Graph-Based Image SegmentationInternational Journal of Computer Vision, 2004
- Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithmIEEE Transactions on Medical Imaging, 2001
- Normalized cuts and image segmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000