Efficient Multiscale Object-based Superpixel Framework
Superpixel segmentation can be used as an intermediary step in many applications, often to improve object delineation and reduce computer workload. However, classical methods do not incorporate information about the desired object. Deep-learning-based approaches consider object information, but their delineation performance depends on data annotation. Additionally, the computational time of object-based methods is usually much higher than desired. In this work, we propose a novel superpixel framework, named Superpixels through Iterative CLEarcutting (SICLE), which exploits object information being able to generate a multiscale segmentation on-the-fly. SICLE starts off from seed oversampling and repeats optimal connectivity-based superpixel delineation and object-based seed removal until a desired number of superpixels is reached. It generalizes recent superpixel methods, surpassing them and other state-of-the-art approaches in efficiency and effectiveness according to multiple delineation metrics.
Code (1)
Tasks
ObjectSegmentationSuperpixelsSimilar Papers 제목 키워드 기반
Image Classification using Graph Neural Network and Multiscale Wavelet Superpixels
Prior studies using graph neural networks (GNNs) for image classification have focused on graphs generated from a regular grid of pixels or similar-sized superpixels. In the latter, a single target number of superpixels …
ClassificationGraph ClassificationGraph Neural Networkimage-classification+2Learning from multiscale wavelet superpixels using GNN with spatially heterogeneous pooling
Neural networks have become the standard for image classification tasks. On one hand, convolutional neural networks (CNNs) achieve state-of-the-art performance by learning from a regular grid representation of images. On…
General ClassificationGraph Classificationimage-classificationImage Classification+1Multiscale Context-Aware Ensemble Deep KELM for Efficient Hyperspectral Image Classification
Recently, multiscale spatial features have been widely utilized to improve the hyperspectral image (HSI) classification performance. However, fixed-size neighborhood involving the contextual information probably leads to…
Computational EfficiencyGeneral ClassificationHyperspectral Image Classificationimage-classification+1MSP : Refine Boundary Segmentation via Multiscale Superpixel
In this paper, we propose a simple but effective message passing method to improve the boundary quality for the semantic segmentation result. Inspired by the generated sharp edges of superpixel blocks, we employ superpix…
Scene ParsingSegmentationSemantic SegmentationExploiting Convolutional Representations for Multiscale Human Settlement Detection
We test this premise and explore representation spaces from a single deep convolutional network and their visualization to argue for a novel unified feature extraction framework. The objective is to utilize and re-purpos…
Transfer Learning