EUVIMEDEUVIMED entdecken
Crossref

Robust Multimodal Learning With Missing Modalities via Parameter-Efficient Adaptation

Md Kaykobad Reza, Ashley Prater-Bennette, M Salman Asif

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-02 · 47 (2) · 742-754

DOI: 10.1109/tpami.2024.3476487 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-02. Verfasst von Md Kaykobad Reza und 2 weiteren Autor:innen. Die Arbeit wurde bisher 73-mal zitiert (Crossref) und nennt 92 Literaturangaben. Gefördert von: Air Force Office of Scientific Research, NSF, Indiana Jetstream2.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multimodal learning seeks to utilize data from multiple sources to improve the overall performance of downstream tasks. It is desirable for redundancies in the data to make multimodal systems robust to missing or corrupted observations in some correlated modalities. However, we observe that the performance of several existing multimodal networks significantly deteriorates if one or multiple modalities are absent at test time. To enable robustness to missing modalities, we propose a simple and parameter-efficient adaptation procedure for pretrained multimodal networks. In particular, we exploit modulation of intermediate features to compensate for the missing modalities. We demonstrate that such adaptation can partially bridge performance drop due to missing modalities and outperform independent, dedicated networks trained for the available modality combinations in some cases. The proposed adaptation requires extremely small number of parameters (e.g., fewer than 1% of the total parameters) and applicable to a wide range of modality combinations and tasks. We conduct a series of experiments to highlight the missing modality robustness of our proposed method on five different multimodal tasks across seven datasets. Our proposed method demonstrates versatility across various tasks and datasets, and outperforms existing methods for robust multimodal learning with missing modalities.

Förderung

  • Air Force Office of Scientific Research
  • NSF
  • Indiana Jetstream2

Zitieren

APA

Reza, M. K., Prater-Bennette, A., & Asif, M. S. (2025). Robust Multimodal Learning With Missing Modalities via Parameter-Efficient Adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(2), 742-754. https://doi.org/10.1109/tpami.2024.3476487

Vancouver

Reza MK, Prater-Bennette A, Asif MS. Robust Multimodal Learning With Missing Modalities via Parameter-Efficient Adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(2):742-754. doi:10.1109/tpami.2024.3476487

BibTeX
@article{Reza2025,
  author = {Reza, Md Kaykobad and Prater-Bennette, Ashley and Asif, M Salman},
  title = {Robust Multimodal Learning With Missing Modalities via Parameter-Efficient Adaptation},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {2},
  pages = {742--754},
  doi = {10.1109/tpami.2024.3476487}
}
Kostenlos starten →