paper-with-me

Papers

Efficient Multiscale Object-based Superpixel Framework

2022-04-07 · Felipe Belém, Benjamin Perret, Jean Cousty, Silvio J. F. Guimarães, Alexandre Falcão

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.

📄 PDF Abstract BibTeX arXiv:2204.03533

Code (1)

lids-unicamp/sicle 공식 구현

Tasks

ObjectSegmentationSuperpixels

Similar Papers 제목 키워드 기반

Image Classification using Graph Neural Network and Multiscale Wavelet Superpixels

2022-01-29 · Varun Vasudevan, Maxime Bassenne, Md Tauhidul Islam, Lei Xing

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+2

Learning from multiscale wavelet superpixels using GNN with spatially heterogeneous pooling

2021-01-01 · Maxime Bassenne, Varun Vasudevan, Lei Xing

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+1

Multiscale Context-Aware Ensemble Deep KELM for Efficient Hyperspectral Image Classification

2020-09-22 · Bobo Xi, Jiaojiao Li, Yunsong Li, Rui Song 외

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+1

MSP : Refine Boundary Segmentation via Multiscale Superpixel

2021-12-03 · Jie Zhu, Huabin Huang, Banghuai Li, Yong liu 외

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 Segmentation

Exploiting Convolutional Representations for Multiscale Human Settlement Detection

2017-07-18 · Dalton Lunga, Dilip Patlolla, Lexie Yang, Jeanette Weaver 외

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