ML Anthology

MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrieval

Naoya Sogi, Takashi Shibata, Makoto Terao, Masanori Suganuma, Takayuki Okatani
IJCAI 2025 pp. 1856-1864
doi:10.24963/IJCAI.2025/207 /ijcai/2025/sogi2025ijcai-ms/

Abstract

Result diversification (RD) is a crucial technique in Text-to-Image Retrieval for enhancing the efficiency of a practical application. Conventional methods focus solely on increasing the diversity metric of image appearances. However, the diversity metric and its desired value vary depending on the application, which limits the applications of RD. This paper proposes a novel task called CDR-CA (Contextual Diversity Refinement of Composite Attributes). CDR-CA aims to refine the diversities of multiple attributes, according to the application's context. To address this task, we propose Multi-Source DPPs, a simple yet strong baseline that extends the Determinantal Point Process (DPP) to multi-sources. We model MS-DPP as a single DPP model with a unified similarity matrix based on a manifold representation. We also introduce Tangent Normalization to reflect contexts. Extensive experiments demonstrate the effectiveness of the proposed method.

PDF IJCAI Semantic Scholar

Cite

Text

Sogi et al. "MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrieval." International Joint Conference on Artificial Intelligence, 2025. doi:10.24963/IJCAI.2025/207

Markdown

[Sogi et al. "MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrieval." International Joint Conference on Artificial Intelligence, 2025.](https://mlanthology.org/ijcai/2025/sogi2025ijcai-ms/) doi:10.24963/IJCAI.2025/207

BibTeX

@inproceedings{sogi2025ijcai-ms,
  title     = {{MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrieval}},
  author    = {Sogi, Naoya and Shibata, Takashi and Terao, Makoto and Suganuma, Masanori and Okatani, Takayuki},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {1856-1864},
  doi       = {10.24963/IJCAI.2025/207},
  url       = {https://mlanthology.org/ijcai/2025/sogi2025ijcai-ms/}
}