Results 81 to 90 of about 3,600 (211)

SWAG: Superpixels weighted by average gradients for explanations of CNNs [PDF]

, 2021
Providing an explanation of the operation of CNNs that is both accurate and interpretable is becoming essential in fields like medical image analysis, surveillance, and autonomous driving.
Marshall, David, Kirill Sidorov, Willis, Christopher, Christopher Willis, Thomas Hartley, David Marshall, Hartley, Thoma, Sidorov, Kirill   +7 more
core   +1 more source

A Bridge Transformer Network With Deep Graph Convolution for Hyperspectral Image Classification

CAAI Transactions on Intelligence Technology, Volume 11, Issue 2, Page 464-482, April 2026.
ABSTRACT Transformers have been widely applied to hyperspectral image classification, leveraging their self‐attention mechanism for powerful global modelling. However, two key challenges remain as follows: excessive memory and computational costs from calculating correlations between all tokens (especially as image size or spectral bands increase) and ...
Yuquan Gan, Siyu Wu, Chang Su, Nan Xiang, Zhijie Xu, Yushan Pan   +5 more
wiley   +1 more source

Superpixels Generation of RGB-D Images Based on Geodesic Distance

, 2015
A novel algorithm for generating superpixels of RGB-D images is presented in this paper. A regular triangular mesh is constructed by the depth and a local geometric features sensitive initialization method is proposed for initializing seeds by a density ...
Pan, Xiao, Zhou, Yuanfeng, Liu, Shuwei, Zhang, Caiming   +3 more
core   +1 more source

Interpretable Machine Learning: A Comprehensive Review of Foundations, Methods, and the Path Forward

WIREs Data Mining and Knowledge Discovery, Volume 16, Issue 1, March 2026.
This systematic review of 352 studies establishes a comprehensive taxonomy for Interpretable Machine Learning, transitioning from foundational intrinsic models to advanced deep learning explanations. It reveals a critical paradigm shift toward “mechanistic interpretability” and actionable recourse, emphasizing that future AI systems must be rigorously ...
Shimon Fridkin, Michael Bendersky
wiley   +1 more source

A Random Walker Algorithm for Plate Boundary Detection in Spherical Mantle Convection Models and Global Geophysical Data Sets: Application to Euler Vector Determination

Journal of Geophysical Research: Solid Earth, Volume 131, Issue 3, March 2026.
Abstract As spherical shell mantle convection models become increasingly commonplace, understanding how plates are generated has raised the issue of how to recognize whether rigid plates are present in model output. Tectonocists have long recognized that intraplate regions are not rigid without exception.
P. Javaheri, J. P. Lowman
wiley   +1 more source

Evaluating UAV Multispectral Imagery, Machine Learning and Image Analysis Techniques for Mapping Taro and Sweet Potato in a Smallholder Cropland in Swayimane, South Africa

Geo: Geography and Environment, Volume 13, Issue 1, January‐June 2026.
Short Abstract This study evaluates the effectiveness of UAV multispectral imagery combined with machine learning techniques for mapping neglected and underutilised crop species (NUS), specifically taro and sweet potato in smallholder farming systems in South Africa.
Mishkah Abrahams, Mbulisi Sibanda, Timothy Dube, James Magidi, Richard Kunz, Vimbayi G. P. Chimonyo, Alistair D. Clulow, Tafadzwanashe Mabhaudhi   +7 more
wiley   +1 more source

SuperBE: computationally light background estimation with superpixels

, 2018
This paper presents a motion-based superpixel-level background estimation algorithm that aims to be competitively accurate while requiring less computation time for background modelling and updating.
Morteza Biglari-Abhari, Andrew Tzer-Yeu Chen, Kevin I-Kai Wang, Chen, Andrew, Biglari-Abhari, Morteza, Wang, Kevin I-Kai   +5 more
core   +1 more source

Superpixel Estimation for Hyperspectral Imagery [PDF]

2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2014
In the past decade, there has been a growing need for machine learning and computer vision components (segmentation, classification) in the hyperspectral imaging domain. Due to the complexity and size of hyperspectral imagery and the enormous number of wavelength channels, the need for combining compact representations with image segmentation and ...
Pegah Massoudifar, Anand Rangarajan 0001, Paul D. Gader   +2 more
openaire   +1 more source

Stereoscopic Saliency Detection for Rail Surface Defects via Global Low‐Rank Reconstruction and Depth Outlier Fusion

Electronics Letters, Volume 62, Issue 1, January/December 2026.
This letter presents an unsupervised stereoscopic saliency detection method for rail surface defects that integrates global low‐rank reconstruction with depth outlier analysis. A binocular line‐scanning system simultaneously acquires RGB images and depth maps, with a Global Low‐Rank Nonnegative Reconstruction (GLRNNR) algorithm extracting 2D saliency ...
Zhiwen Xiong, Yuanchun Li
wiley   +1 more source

Robust Active Contour Model for Image Segmentation Using a Probability Density Function Approach

IET Image Processing, Volume 20, Issue 1, January/December 2026.
This paper proposes an active contour model‐based image segmentation algorithm using the probability density function. Initially, the probability density function is defined by the local mean and variance. Next, a length penalty term and a distance regularization term are incorporated.
XinChao Meng, Si Si, Pei Zhang
wiley   +1 more source