analiza aiqbench
This research advances semi-supervised image classification by leveraging Graph Neural Networks (GNNs) to fuse complementary representations from diverse feature extractors like CNNs and Vision Transformers. The study demonstrates that strategically combining these heterogeneous data sources, alongside manifold learning techniques for graph construction, significantly boosts accuracy in low-label regimes. This work highlights the growing utility of GNN architectures as a robust framework for integrating multi-modal visual information without relying on quantum mechanics or general consumer tech trends.
Graph Neural Networks for Semi-Supervised Image Classification with Multi-Feature Aggregation
arXiv:2606.17406v1 Announce Type: cross Abstract: Feature extraction involves the identification and extraction of salient characteristics or patterns, including edges, textures, shapes, and color attributes. Contemporary feature extractors predominantly leverage deep learning architectures, such as Convolutional Neural Networks (CNNs) and Vision Transformers (VITs). The availability of diverse feature extractors in the literature provides a wide range of feature representations. Features extracted from an image depend on the specific application, the chosen extractor, and its configuration. Therefore, integrating complementary information by combining distinct extractors offers a promising way to enhance performance. Graph Neural Networks (GNNs), particularly Graph Convolutional Networks (GCNs), have emerged as powerful and widely adopted approaches for semi-supervised image classification, as they effectively leverage both labeled and unlabeled data while exploiting the underlying graph structures that capture relationships among samples. This study proposes a novel approach for GNNs in scenarios where labeled data is scarce, by integrating diverse sets of feature and graph representations derived from various extractors in classification scenarios. Experimental investigations were conducted, encompassing combinations of distinct feature and graph extractors, as well as rank aggregation strategies. The primary contributions of this work are underscored by the experimental findings, which demonstrate that the strategic combination of feature and graph representations, coupled with the application of manifold learning for graph processing, leads to significant improvements in classification accuracy across the majority of experimental conditions. Furthermore, the utilization of rank aggregation techniques to integrate features from different extractors was shown to enhance classification accuracy.
Abstract:Feature extraction involves the identification and extraction of salient characteristics or patterns, including edges, textures, shapes, and color attributes. Contemporary feature extractors predominantly leverage deep learning architectures, such as Convolutional Neural Networks (CNNs) and Vision Transformers (VITs). The availability of diverse feature extractors in the literature provides a wide range of feature representations. Features extracted from an image depend on the specific application, the chosen extractor, and its configuration. Therefore, integrating complementary information by combining distinct extractors offers a promising way to enhance performance. Graph Neural Networks (GNNs), particularly Graph Convolutional Networks (GCNs), have emerged as powerful and widely adopted approaches for semi-supervised image classification, as they effectively leverage both labeled and unlabeled data while exploiting the underlying graph structures that capture relationships among samples. This study proposes a novel approach for GNNs in scenarios where labeled data is scarce, by integrating diverse sets of feature and graph representations derived from various extractors in classification scenarios. Experimental investigations were conducted, encompassing combinations of distinct feature and graph extractors, as well as rank aggregation strategies. The primary contributions of this work are underscored by the experimental findings, which demonstrate that the strategic combination of feature and graph representations, coupled with the application of manifold learning for graph processing, leads to significant improvements in classification accuracy across the majority of experimental conditions. Furthermore, the utilization of rank aggregation techniques to integrate features from different extractors was shown to enhance classification accuracy.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2606.17406 [cs.CV]
(or arXiv:2606.17406v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2606.17406 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 339 cuvinte
Subiecte conexe
Context-Aware Interpretable Representations for Retrieval and Graph Convolutional Network Classification
arXiv · 1 sept. 2026
GLL: A Differentiable Graph Learning Layer for Neural Networks
arXiv · 15 oct. 2026
DeltaGNN: Graph Neural Network with Information Flow Control
arXiv · 25 aug. 2026
When Does the Dependency Graph Help Code-to-Architecture Mapping?
arXiv · 15 oct. 2026