Results 81 to 90 of about 10,393 (248)

Beyond KernelBoost [PDF]

, 2014
In this Technical Report we propose a set of improvements with respect to the KernelBoost classifier presented in [Becker et al., MICCAI 2013]. We start with a scheme inspired by Auto-Context, but that is suitable in situations where the lack of large ...
Fua, Pascal, Lepetit, Vincent, Rigamonti, Roberto   +2 more
core   +1 more source

A survey on the utilization of Superpixel image for clustering based image segmentation [PDF]

, 2023
Buddhadev Sasmal, Krishna Gopal Dhal
openalex   +1 more source

Geometry-based Superpixel Segmentation - Introduction of Planar Hypothesis for Superpixel Construction

Proceedings of the 10th International Conference on Computer Vision Theory and Applications, 2015
Superpixel segmentation is widely used in the preprocessing step of many applications. Most of existing methods are based on a photometric criterion combined to the position of the pixels. In the same way as the Simple Linear Iterative Clustering (SLIC) method, based on k-means segmentation, a new algorithm is introduced.
Bauda, Marie-Anne, Chambon, Sylvie, Gurdjos, Pierre, Charvillat, Vincent   +3 more
openaire   +2 more sources

Relieve the Demand for Labeled Data of Deep Learning Models for Hydraulic Conductivity Field Tasks in Groundwater Through Self‐Supervised Learning

Journal of Geophysical Research: Machine Learning and Computation, Volume 2, Issue 4, December 2025.
Abstract Deep learning (DL) has shown great potential in solving groundwater problems but often requires large labeled data sets, which are expensive and time‐consuming to obtain. In this study, we introduce a self‐supervised learning approach based on a masked autoencoder (MAE)—an encoder‐decoder architecture that reconstructs randomly masked input ...
Kai Ji, Zhengkun Zhou, Bo Zou, Ruiting Yang, Baoqing Zhang   +4 more
wiley   +1 more source

GASP : Geometric Association with Surface Patches

, 2014
A fundamental challenge to sensory processing tasks in perception and robotics is the problem of obtaining data associations across views. We present a robust solution for ascertaining potentially dense surface patch (superpixel) associations, requiring ...
Christensen, Henrik I., Li, Fuxin, Sawhney, Rahul   +2 more
core   +1 more source

Selective Multiple Classifiers for Weakly Supervised Semantic Segmentation

CAAI Transactions on Intelligence Technology, Volume 10, Issue 6, Page 1688-1702, December 2025.
ABSTRACT Existing weakly supervised semantic segmentation (WSSS) methods based on image‐level labels always rely on class activation maps (CAMs), which measure the relationships between features and classifiers. However, CAMs only focus on the most discriminative regions of images, resulting in their poor coverage performance.
Zilin Guo, Dongyue Wu, Changxin Gao, Nong Sang   +3 more
wiley   +1 more source

An unsupervised semantic segmentation method that combines the ImSE-Net model with SLICm superpixel optimization

International Journal of Digital Earth
In the field of remote sensing, using a large amount of labeled image data to supervise the training of fully convolutional networks for the semantic segmentation of images is expensive.
Zenan Yang, Haipeng Niu, Xiaoxuan Wang, Liang Huang, Kui Yang   +4 more
doaj   +1 more source

Integrated Deep and Shallow Networks for Salient Object Detection

, 2017
Deep convolutional neural network (CNN) based salient object detection methods have achieved state-of-the-art performance and outperform those unsupervised methods with a wide margin.
Dai, Yuchao, He, Mingyi, Li, Bo, Porikli, Fatih, Zhang, Jing   +4 more
core   +1 more source

Dual‐state six‐channel polarization multiplexing in reconfigurable metasurfaces

Nanophotonics, Volume 14, Issue 25, Page 4583-4593, December 2025.
Abstract Dynamically tunable metasurfaces based on phase‐change materials (PCMs) have become important platforms for realizing reconfigurable optical systems. Nevertheless, achieving multiple independent functionalities within a single device, particularly under polarization multiplexing, remains difficult due to limited design flexibility.
Sujun Xie, Tianxu Jia, Xiaoyue Ma, Bingjue Li, Ruohu Zhang, Zhigang Li, Binfeng Yun, Hyeonsu Heo, Nara Jeon, Guanghao Rui, Junsuk Rho   +10 more
wiley   +1 more source

Image Parsing with a Wide Range of Classes and Scene-Level Context

, 2015
This paper presents a nonparametric scene parsing approach that improves the overall accuracy, as well as the coverage of foreground classes in scene images. We first improve the label likelihood estimates at superpixels by merging likelihood scores from
George, Marian
core   +1 more source