Superpixels
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Robust Semantic Segmentation with Superpixel-Mix
Iterative, Deep, and Unsupervised Synthetic Aperture Sonar Image Segmentation
Superpixel-guided Iterative Learning from Noisy Labels for Medical Image Segmentation
PDC: Piecewise Depth Completion utilizing Superpixels
ESCNet: An End-to-End Superpixel-Enhanced Change Detection Network for Very-High-Resolution Remote Sensing Images
Unsupervised Image Segmentation by Mutual Information Maximization and Adversarial Regularization
Fast whole-slide cartography in colon cancer histology using superpixels and CNN classification
Survey of Image Based Graph Neural Networks
HERS Superpixels: Deep Affinity Learning for Hierarchical Entropy Rate Segmentation
Superpixel-based Knowledge Infusion in Deep Neural Networks for Image Classification
Superpixels and Graph Convolutional Neural Networks for Efficient Detection of Nutrient Deficiency Stress from Aerial Imagery
ManhattanSLAM: Robust Planar Tracking and Mapping Leveraging Mixture of Manhattan Frames
Deep Superpixel Cut for Unsupervised Image Segmentation
Implicit Integration of Superpixel Segmentation into Fully Convolutional Networks
Unsupervised semantic discovery through visual patterns detection
Tech Report: A Homogeneity-Based Multiscale Hyperspectral Image Representation for Sparse Spectral Unmixing
What does LIME really see in images?
Power-SLIC: Fast Superpixel Segmentations by Diagrams
Semi-supervised Hyperspectral Image Classification with Graph Clustering Convolutional Networks
Rethinking Road Surface 3D Reconstruction and Pothole Detection: From Perspective Transformation to Disparity Map Segmentation
Superpixel Segmentation Based on Spatially Constrained Subspace Clustering
Refining Semantic Segmentation with Superpixel by Transparent Initialization and Sparse Encoder
Explaining Deep Neural Networks
Visual Object Tracking by Segmentation with Graph Convolutional Network
Fuzzy SLIC: Fuzzy Simple Linear Iterative Clustering
An Explainable Machine Learning Model for Early Detection of Parkinson's Disease using LIME on DaTscan Imagery
Superpixel Based Graph Laplacian Regularization for Sparse Hyperspectral Unmixing
Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation
COV-ELM classifier: An Extreme Learning Machine based identification of COVID-19 using Chest X-Ray Images
P$^{2}$Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation
Superpixel Segmentation using Dynamic and Iterative Spanning Forest
Affinity Fusion Graph-based Framework for Natural Image Segmentation
Non-parametric spatially constrained local prior for scene parsing on real-world data
SLIC-UAV: A Method for monitoring recovery in tropical restoration projects through identification of signature species using UAVs
Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.