all AI news
Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation
Feb. 27, 2024, 5:44 a.m. | Md Kaykobad Reza, Ashley Prater-Bennette, M. Salman Asif
cs.LG updates on arXiv.org arxiv.org
Abstract: 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 …
abstract arxiv cs.cv cs.lg data multimodal multimodal learning multimodal systems multiple observe performance robust systems tasks type via
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Data Science Analyst
@ Mayo Clinic | AZ, United States
Sr. Data Scientist (Network Engineering)
@ SpaceX | Redmond, WA