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.
Superpixel Segmentation with Fully Convolutional Networks
Co-occurrence Background Model with Superpixels for Robust Background Initialization
Texture Superpixel Clustering from Patch-based Nearest Neighbor Matching
Multi-Scale Superpatch Matching using Dual Superpixel Descriptors
Superpixel Segmentation via Convolutional Neural Networks with Regularized Information Maximization
Superpixel Image Classification with Graph Attention Networks
Two-Phase Object-Based Deep Learning for Multi-temporal SAR Image Change Detection
The Semantic Mutex Watershed for Efficient Bottom-Up Semantic Instance Segmentation
ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation
Superpixel-Based Background Recovery from Multiple Images
Resolution-independent meshes of super pixels
Effect of Superpixel Aggregation on Explanations in LIME -- A Case Study with Biological Data
Superpixel Tensor Pooling for Visual Tracking using Multiple Midlevel Visual Cues Fusion
Dynamic Spectral Residual Superpixels
Learning Propagation for Arbitrarily-structured Data
A superpixel-driven deep learning approach for the analysis of dermatological wounds
Real-time Scalable Dense Surfel Mapping
Deep Green Function Convolution for Improving Saliency in Convolutional Neural Networks
A Blind Multiscale Spatial Regularization Framework for Kernel-based Spectral Unmixing
Gradient Weighted Superpixels for Interpretability in CNNs
Recognizing Image Objects by Relational Analysis Using Heterogeneous Superpixels and Deep Convolutional Features
Image Classification with Hierarchical Multigraph Networks
GASP, a generalized framework for agglomerative clustering of signed graphs and its application to Instance Segmentation
Closed-Loop Adaptation for Weakly-Supervised Semantic Segmentation
Segmentation-Aware Hyperspectral Image Classification
RGB-T Image Saliency Detection via Collaborative Graph Learning
SCALP: Superpixels with Contour Adherence using Linear Path
SuperPatchMatch: an Algorithm for Robust Correspondences using Superpixel Patches
Robust superpixels using color and contour features along linear path
Superpixel-based Color Transfer
Superpixel Contracted Graph-Based Learning for Hyperspectral Image Classification
Generating superpixels using deep image representations
Unsupervised learning-based long-term superpixel tracking
Texture-Aware Superpixel Segmentation
Texture Relative Superpixel Generation With Adaptive Parameters
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.