Fast Component Tree Computation for Images of Limited Levels

Tao, Rui; Qiao, Jing

doi:10.1109/tpami.2022.3180827

Cited by 2 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Step 1: For a particular pixel, 𝑝𝑖𝑥𝑒𝑙 𝑖 in the image, use the pixel as the center and perform proposal frame growth with 8-CONNECTIVITY [53]. Record the 𝐷𝑆 𝑙𝑜𝑐 after growing each proposal frame.…”

Section: Fig 2 the Framework Of Proposal Frame Extraction For Local L...mentioning

confidence: 99%

Zero-Shot Remote Sensing Scene Classification Method Based on Local-Global Feature Fusion and Weight Mapping Loss

Wang,

Li,

Tanvir

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Zero-shot remote sensing scene classification refers to making the model to have the ability to identify the unseen class scenes based on seen class scenes, and has become a research hotspot in the field of remote sensing. Contemporary approaches in zero-shot remote sensing scene classification primarily focus on extracting global information from scenes, neglecting nuanced local landscape features. This oversight diminishes the discriminative capabilities of recognition models. Furthermore, these methods overlook the semantic relevance between seen and unseen class scenes in training, leading to reduced emphasis on learning from varied scenes and subsequent declines in classification performance. To address these challenges, this paper proposes the "Zero-Shot Remote Sensing Scene Classification Method Based on Local-Global Feature Fusion and Weight Mapping Loss (LGFFWM)." The design incorporates a local-global feature fusion (LGFF) module enabling adaptive labeling and feature modeling of internal local landscapes, effectively merging them with global features for a more discriminative representation of remote sensing scenes. Furthermore, a weight mapping loss (WM Loss) function is introduced, leveraging a semantic correlation matrix to compel the model to prioritize learning seen class scenes that exhibit strong correlations with unseen class scenes by assigning higher training weights. Extensive experiments have been conducted on classical remote sensing scene datasets, including UCM, AID, and NWPU, demonstrate the superiority of the proposed LGFFWM method over ten advanced comparative methods, yielding overall accuracy improvements of over 2.25%, 3.47%, and 0.44%, respectively. Additional experiments on the SIRI-WHU and RSSCN7 datasets underscore the transferability of LGFFWM, achieving overall accuracies of 53.50% and 47.37%, respectively.

show abstract

Section: Fig 2 the Framework Of Proposal Frame Extraction For Local L...mentioning

confidence: 99%

Zero-Shot Remote Sensing Scene Classification Method Based on Local-Global Feature Fusion and Weight Mapping Loss

Wang,

Li,

Tanvir

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Within the literature dedicated to the construction of the component-tree and the tree of shapes, some algorithms rely on the first to build the second [6,3] or vice versa [28]. This is motivated by the strong links that exist between them.…”

Section: Related Workmentioning

confidence: 99%

Building the Topological Tree of Shapes from the Tree of Shapes

Mendes Forte,

Passat,

Kenmochi

2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The topological tree of shapes was recently introduced as a new hierarchical structure within the family of morphological trees. Morphological trees are efficient models for image processing and analysis. For such applications, it is of paramount importance that these structures be built and manipulated with optimal complexity. In this article, we focus on the construction of the topological tree of shapes. We propose an algorithm for building the topological tree of shapes from the tree of shapes. In particular, a cornerstone of this algorithm is the construction of the complete tree of shapes, another recently introduced tree unifying both the tree of shapes and the topological tree of shapes. We also discuss the cost of the computation of these structures.

show abstract

Fast Component Tree Computation for Images of Limited Levels

Cited by 2 publications

References 37 publications

Zero-Shot Remote Sensing Scene Classification Method Based on Local-Global Feature Fusion and Weight Mapping Loss

Zero-Shot Remote Sensing Scene Classification Method Based on Local-Global Feature Fusion and Weight Mapping Loss

Building the Topological Tree of Shapes from the Tree of Shapes

Contact Info

Product

Resources

About