SOTAVerified

Superpixels

Superpixel techniques segment an image into regions based on similarity measures that utilize perceptual features, effectively grouping pixels that appear similar. The motivation behind this approach is to generate regions that provide meaningful descriptions while significantly reducing the data volume compared to using every individual pixel. By decreasing the number of primitives, these techniques reduce redundancy and simplify the complexity of recognition tasks. Superpixels replace the rigid structure of individual pixels with delineated regions that preserve meaningful content in the image, thereby aiding the interpretation of the scene’s structure and simplifying subsequent processing tasks. Generally, superpixel techniques rely on measures that evaluate color similarities and the shapes of regions, incorporating edges or significant changes in intensity to define these regions.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 276–300 of 371 papers

TitleStatusHype
Rethinking Superpixel Segmentation from Biologically Inspired Mechanisms—0
Rethinking Unsupervised Neural Superpixel Segmentation—0
Revisiting Superpixels for Active Learning in Semantic Segmentation With Realistic Annotation Costs—0
Robust deep learning-based semantic organ segmentation in hyperspectral images—0
Robust Region Grouping via Internal Patch Statistics—0
Robust superpixels using color and contour features along linear path—0
Saliency Detection via Bidirectional Absorbing Markov Chain—0
Saliency Detection via Graph-Based Manifold Ranking—0
Iterative Saliency Enhancement using Superpixel Similarity—0
Sample and Filter: Nonparametric Scene Parsing via Efficient Filtering—0
Scalable Simple Linear Iterative Clustering (SSLIC) Using a Generic and Parallel Approach—0
SCALP: Superpixels with Contour Adherence using Linear Path—0
Scene Labeling Using Beam Search Under Mutex Constraints—0
Segmentation-aware Deformable Part Models—0
Segmentation-Aware Hyperspectral Image Classification—0
Semantic 3D Occupancy Mapping through Efficient High Order CRFs—0
Semantic Component Analysis—0
Semantic interpretation for convolutional neural networks: What makes a cat a cat?—0
Semantic Object Parsing with Graph LSTM—0
Semi-Automated Segmentation of Geoscientific Data Using Superpixels—0
Semi-supervised Hyperspectral Image Classification with Graph Clustering Convolutional Networks—0
Semi-supervised Learning with Graphs: Covariance Based Superpixels For Hyperspectral Image Classification—0
Single Target Tracking Using Adaptive Clustered Decision Trees and Dynamic Multi-Level Appearance Models—0
Single-View 3D Scene Parsing by Attributed Grammar—0
SP ^3 : Superpixel-propagated pseudo-label learning for weakly semi-supervised medical image segmentation—0
Show:102550
← PrevPage 12 of 15Next →

No leaderboard results yet.