Metraipolis › archive › dc_c19beecb102a

MSGAT: Multi-Head Spiking Graph Attention with Similarity-Space Fusion for Image-Text Retrieval — arXiv:2610.11526

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.11526
License (as archived): CC0-1.0
Archived: 2026-10-09T06:00:04.311Z
SHA-256 of the archived text: 6a323153d06efdde6191dce2adac6b0cf8b5d19117f9296dfb264df86b08cc82
Stable URL of this page: https://metraipolis.com/documento/dc_c19beecb102a

How to cite

MSGAT: Multi-Head Spiking Graph Attention with Similarity-Space Fusion for Image-Text Retrieval — arXiv:2610.11526 — arXiv (en), https://arxiv.org/abs/2610.11526 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c19beecb102a (Metraipolis archive dc_c19beecb102a, sha256 6a323153d06efdde6191dce2adac6b0cf8b5d19117f9296dfb264df86b08cc82)

BibTeX

@misc{dcc19beecb102a,
  title = {MSGAT: Multi-Head Spiking Graph Attention with Similarity-Space Fusion for Image-Text Retrieval — arXiv:2610.11526},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11526},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c19beecb102a; sha256 6a323153d06efdde6191dce2adac6b0cf8b5d19117f9296dfb264df86b08cc82},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11526. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Spiking neural networks (SNNs) offer an energy-efficient computing paradigm through sparse event-driven computation, showing great potential for efficient multimodal learning. However, applying SNNs to high-level multimodal tasks, such as image-text retrieval (ITR), remains challenging, since sparse spike representations make it difficult to capture semantic structures required for cross-modal alignment. Existing spiking ITR methods rely on local alignment and additional soft-label supervision during training, while lacking awareness of structural and multi-granularity relationships. To address these issues, we propose a Multi-head Spiking Graph Attention Network (\textbf{MSGAT}) for structural modeling and equip it with dynamic attention heads to capture complementary relational patterns and enable spike-driven graph reasoning and aggregation. However, within a two-branch multi-granularity fusion framework, the fine-grained spike representations generated by MSGAT are sparse and discrete, whereas the global representations are continuous, making conventional feature-level fusion susceptible to interference across heterogeneous representations. Therefore, we introduce \textbf{Sim-Fuse}, a similarity-space fusion alignment strategy integrating coarse- and fine-grained matching relations while avoiding direct fusion of heterogeneous representations. Experiments on Flickr30K and MSCOCO show our method outperforms ANN methods under matched settings and existing SNN retrieval baselines. Moreover, with only two time steps, our SNN achieves comparable or superior performance to its ANN counterpart while reducing theoretical module-level energy by 55\%. The code is provided in the Supplementary Materials.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.11526 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T05:47:01.707Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).