EUVIMEDEUVIMED entdecken
Crossref

Multi-Branch Tree-Based Fusion Neural Architecture Search With Zero-Cost Screen for Multi-Modal Classification

Qian Guo, Quanchen Su, Xinyan Liang, Yuhua Qian, Nan Li, Zhihua Cui

IEEE Transactions on Image Processing · 2026 · 35 · 7192-7205

DOI: 10.1109/tip.2026.3706305 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Qian Guo und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 71 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-modal classification (MMC) leverages effective fusion of information from diverse modalities to achieve superior classification performance. Existing fusion methods, however, rely on expert-designed architectures that demand substantial domain expertise and computational resources, with fixed topologies that offer limited structural flexibility across tasks and datasets. Although neural architecture search (NAS)-based fusion methods have been proposed to automatically discover high-performing architectures, these approaches are computationally expensive and predominantly rely on pairwise modality combinations, which fail to capture complex multi-variable correlations, limiting the architectures' expressiveness and flexibility. Consequently, there remains a lack of multi-modal fusion frameworks that can simultaneously achieve high efficiency and high accuracy. To break through these bottlenecks, we propose a multi-branch tree-based fusion neural architecture search framework (MBTF-NAS). For performance enhancement, MBTF-NAS employs a multi-branch tree-structured encoding strategy that enables dynamic and computationally efficient exploration of fusion topologies and substantially strengthens cross-modal interaction. A learnable model-level attention weighting mechanism further emphasizes informative modalities, improving the overall quality of multi-modal feature fusion. For efficiency improvement, MBTF-NAS leverages zero-cost proxy metrics for architecture evaluation, enabling rapid identification of high-potential candidates while dramatically reducing computational overhead. We conducted a comprehensive evaluation of MBTF-NAS on seven representative multi-modal benchmarks. The experimental results demonstrate that MBTF-NAS consistently outperforms state-of-the-art approaches, highlighting its effectiveness and generalizability.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Guo, Q., Su, Q., Liang, X., Qian, Y., Li, N., & Cui, Z. (2026). Multi-Branch Tree-Based Fusion Neural Architecture Search With Zero-Cost Screen for Multi-Modal Classification. IEEE Transactions on Image Processing, 35, 7192-7205. https://doi.org/10.1109/tip.2026.3706305

Vancouver

Guo Q, Su Q, Liang X, Qian Y, Li N, Cui Z. Multi-Branch Tree-Based Fusion Neural Architecture Search With Zero-Cost Screen for Multi-Modal Classification. IEEE Transactions on Image Processing. 2026;35:7192-7205. doi:10.1109/tip.2026.3706305

BibTeX
@article{Guo2026,
  author = {Guo, Qian and Su, Quanchen and Liang, Xinyan and Qian, Yuhua and Li, Nan and Cui, Zhihua},
  title = {Multi-Branch Tree-Based Fusion Neural Architecture Search With Zero-Cost Screen for Multi-Modal Classification},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  volume = {35},
  pages = {7192--7205},
  doi = {10.1109/tip.2026.3706305}
}
Kostenlos starten →