End-to-end trainable network for superpixel and image segmentation

Abstract Image segmentation and superpixel generation have been studied for many years, and they are still active research topics in computer vision. Although many advanced computer vision algorithms have been used for image segmentation and superpixel generation, there is no end-to-end trainable algorithm that generates superpixels and segment images simultaneously. We propose an end-to-end trainable network to solve this problem. We train a differentiable clustering algorithm module to produce accurate superpixels. Based on the generated superpixels, the superpixel pooling operation is performed to obtain superpixel features, and then we calculate the similarity of two adjacent superpixels. If the similarity is greater than the preset threshold, we merge the two superpixels. Finally, we get the segmented image. We conduct our experiments in the BSDS500 dataset and get good results.

• Publication year

  2020

• Venue

  Pattern Recognition Letters

• Publication date

  2020-12-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1016/J.PATREC.2020.09.016
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Unsupervised learning-based long-term superpixel tracking

  2019cited by this paper
• Superpixel-Based Fast Fuzzy C-Means Clustering for Color Image Segmentation

  2019cited by this paper
• Learning contextual superpixel similarity for consistent image segmentation

  2019cited by this paper
• Automatic Image Segmentation With Superpixels and Image-Level Labels

  2019cited by this paper
• Group Normalization

  2018cited by this paper
• Unified Perceptual Parsing for Scene Understanding

  2018cited by this paper
• Learning Pixel-Level Semantic Affinity with Image-Level Supervision for Weakly Supervised Semantic Segmentation

  2018cited by this paper
• DEL: Deep Embedding Learning for Efficient Image Segmentation

  2018cited by this paper
• Superpixel Sampling Networks

  2018influential reference
• Weakly Supervised Semantic Segmentation Using Superpixel Pooling Network

  2017influential reference
• Selective Search for Object Recognition

  2016cited by this paper
• FLIC: Fast linear iterative clustering with active search

  2016cited by this paper
• Scale-Aware Alignment of Hierarchical Image Segmentation

  2016cited by this paper
• SuperCNN: A Superpixelwise Convolutional Neural Network for Salient Object Detection

  2015cited by this paper
• Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation

  2015cited by this paper
• Superpixel segmentation using Linear Spectral Clustering

  2015cited by this paper
• Superpixel Convolutional Networks Using Bilateral Inceptions

  2015cited by this paper
• Watershed superpixel

  2015cited by this paper
• Object detection by labeling superpixels

  2015cited by this paper
• Fully convolutional networks for semantic segmentation

  2014influential reference
• Robust Superpixel Tracking

  2014cited by this paper
• Recursive Context Propagation Network for Semantic Scene Labeling

  2014cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Saliency Optimization from Robust Background Detection

  2014cited by this paper
• Caffe: Convolutional Architecture for Fast Feature Embedding

  2014cited by this paper
• Blocks That Shout: Distinctive Parts for Scene Classification

  2013cited by this paper
• Saliency Detection via Graph-Based Manifold Ranking

  2013cited by this paper
• Improving an Object Detector and Extracting Regions Using Superpixels

  2013cited by this paper
• SLIC Superpixels Compared to State-of-the-Art Superpixel Methods

  2012cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• Superpixel tracking

  2011cited by this paper
• Contour Detection and Hierarchical Image Segmentation

  2011influential reference
• Multi-Class Segmentation with Relative Location Prior

  2008cited by this paper
• Robust Higher Order Potentials for Enforcing Label Consistency

  2008cited by this paper
• Efficient Graph-Based Image Segmentation

  2004cited by this paper
• Learning a classification model for segmentation

  2003cited by this paper
• Normalized cuts and image segmentation

  1997cited by this paper

• FW-S3PFCM: feature-weighted safe-semi-supervised possibilistic fuzzy C-means clustering

  2026cites this paper
• Joint multi-dimension features fuzzy clustering algorithm based on smoothing superpixel for sonar image segmentation

  2025cites this paper
• Efficient superpixel-based brain MRI segmentation using multi-scale morphological gradient reconstruction and quantum clustering

  2025cites this paper
• A Comprehensive Review and New Taxonomy on Superpixel Segmentation

  2024cites this paper
• Detail preserving conditional random field as 2-D RNN for gland segmentation in histology images

  2022cites this paper
• Point Label Aware Superpixels for Multi-Species Segmentation of Underwater Imagery

  2022cites this paper
• Two-stream interactive network based on local and global information for No-Reference Stereoscopic Image Quality Assessment

  2022cites this paper
• Automatic Superpixel-Based Clustering for Color Image Segmentation Using q-Generalized Pareto Distribution under Linear Normalization and Hunger Games Search

  2021cites this paper
• Super-pixel Segmentation based Skin texture pattern recognition

  2021cites this paper
• CGFFCM: Cluster-weight and Group-local Feature-weight learning in Fuzzy C-Means clustering algorithm for color image segmentation

  2021cites this paper
• Extended set of superpixel features

  2021cites this paper