Hierarchical classification based on coarse- to fine-grained knowledge transfer

Qiu, Zeyu; Hu, Minjie; Zhao, Hong

doi:10.1016/j.ijar.2022.07.002

Cited by 5 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The multi-branch structure aims to provide separate model parameters for 𝐸𝐸 𝑓𝑓 and 𝐸𝐸 𝑐𝑐 to cope with end-to-end joint training. This structure has been applied in some work to provide hierarchical (i.e., multi-granularity) image classification [19][20][21][22]. In contrast to the independent branching structure, the multi-branching structure employs a shared convolutional network to extract common visual features in the image, which solves part of the parameter redundancy problem.…”

Section: Multi-branch Featrue Extraction Modulementioning

confidence: 99%

AI-Empowered Multimodal Hierarchical Graph-Based Learning for Situation Awareness on Enhancing Disaster Responses

Chen,

Seng,

Ang

et al. 2024

Future Internet

View full text Add to dashboard Cite

Situational awareness (SA) is crucial in disaster response, enhancing the understanding of the environment. Social media, with its extensive user base, offers valuable real-time information for such scenarios. Although SA systems excel in extracting disaster-related details from user-generated content, a common limitation in prior approaches is their emphasis on single-modal extraction rather than embracing multi-modalities. This paper proposed a multimodal hierarchical graph-based situational awareness (MHGSA) system for comprehensive disaster event classification. Specifically, the proposed multimodal hierarchical graph contains nodes representing different disaster events and the features of the event nodes are extracted from the corresponding images and acoustic features. The proposed feature extraction modules with multi-branches for vision and audio features provide hierarchical node features for disaster events of different granularities, aiming to build a coarse-granularity classification task to constrain the model and enhance fine-granularity classification. The relationships between different disaster events in multi-modalities are learned by graph convolutional neural networks to enhance the system’s ability to recognize disaster events, thus enabling the system to fuse complex features of vision and audio. Experimental results illustrate the effectiveness of the proposed visual and audio feature extraction modules in single-modal scenarios. Furthermore, the MHGSA successfully fuses visual and audio features, yielding promising results in disaster event classification tasks.

show abstract

Section: Multi-branch Featrue Extraction Modulementioning

confidence: 99%

AI-Empowered Multimodal Hierarchical Graph-Based Learning for Situation Awareness on Enhancing Disaster Responses

Chen,

Seng,

Ang

et al. 2024

Future Internet

View full text Add to dashboard Cite

show abstract

“…Predefined classification trees are usually derived from specialized fields (such as tree classification) or from the knowledge of experts, while automatically generated classification trees are learned by top-down or bottom-up methods such as hierarchical clustering [32,34]. A large number of studies combine hierarchical classification with CNNs for visual recognition and other applications [35,36]. For example, Yan et al [31] proposed a hierarchical deep CNN (HD-CNN), and its performances were assessed using several datasets, such as the CIFAR 100 class and large-scale ImageNet 1000 benchmark datasets.…”

Section: Introductionmentioning

confidence: 99%

Individual Tree Species Classification Based on a Hierarchical Convolutional Neural Network and Multitemporal Google Earth Images

Lei

Zhao

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Accurate and efficient individual tree species (ITS) classification is the basis of fine forest resource management. It is a challenge to classify individual tree species in dense forests using remote sensing imagery. In order to solve this problem, a new ITS classification method was proposed in this study, in which a hierarchical convolutional neural network (H-CNN) model and multi-temporal high-resolution Google Earth images were employed. In an experiment conducted in a forest park in Beijing, China, GE images of several significant phenological phases of broad-leaved forests, namely, before and after the mushrooming period, the growth period, and the wilting period, were selected, and ITS classifications based on these images along with several typical CNN models and the H-CNN model were conducted. In the experiment, the classification accuracy of the multitemporal images was higher by 7.08–12.09% than those of the single-temporal images, and the H-CNN model offered an OA accuracy 2.66–3.72% higher than individual CNN models, demonstrating that multitemporal images rich in the phenological features of individual tree species, together with a hierarchical CNN model, can effectively improve ITS classification.

show abstract

Hierarchical multi-granularity classification based on bidirectional knowledge transfer

Jiang,

Yang,

Zhang

et al. 2024

Multimedia Systems

View full text Add to dashboard Cite

Hierarchical classification based on coarse- to fine-grained knowledge transfer

Cited by 5 publications

References 32 publications

AI-Empowered Multimodal Hierarchical Graph-Based Learning for Situation Awareness on Enhancing Disaster Responses

AI-Empowered Multimodal Hierarchical Graph-Based Learning for Situation Awareness on Enhancing Disaster Responses

Individual Tree Species Classification Based on a Hierarchical Convolutional Neural Network and Multitemporal Google Earth Images

Hierarchical multi-granularity classification based on bidirectional knowledge transfer

Contact Info

Product

Resources

About