Segment scene unsupervised using pixel clustering with Hoang
Segment scene unsupervised using pixel clustering with Hoang
Pixel-Level Clustering Network for Unsupervised Image Segmentation
arXiv paper abstract https://arxiv.org/abs/2310.16234
arXiv PDF paper https://arxiv.org/pdf/2310.16234.pdf
While image segmentation is crucial in ... computer vision ... annotating all objects at the pixel-level for training is nearly impossible. Therefore ... unsupervised image segmentation methods is essential.
... present a pixel-level clustering framework for segmenting images into regions without using ground truth annotations.
The proposed framework includes feature embedding modules with an attention mechanism, a feature statistics computing module, image reconstruction, and superpixel segmentation to achieve accurate unsupervised segmentation.
... propose a training strategy that utilizes intra-consistency within each superpixel, inter-similarity/dissimilarity between neighboring superpixels, and structural similarity between images.
... present an extension of the proposed method for unsupervised semantic segmentation.
... proposed framework outperforms previous state-of-the-art methods.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments