Research towards AI technologies that facilitate everyday life has strongly emerged during the last years in order to modernize operations and optimize productivity in a wide range of sectors and applications. When referring to the defense domain, AI technologies pose additional challenges, as security matters are under serious consideration to avoid any undesirable disclosure of sensitive information. Data frugality, adaptation in new environments, continuous learning are some of the specificities of the Defense domain that AI technologies need to address.
M4D group combines research from various domains and techniques in order to adapt and reuse already existing developments that can also satisfy the needs of the domain sector. More specifically, M4D performs research activities towards the development of frugal models that can be trained with the use of less or no annotated data via different learning paradigms, in order to tackle the scarcity or unsuitability of training data. In addition, the group’s research experience in fusion techniques will contribute to extract additional knowledge of the outcomes of different modalities in a complementary manner, and provide improved situational awareness and decision supporting schemas to the operators.
