-- Context --
Project ABYSSES (Boosted Annotations of 3D models of deep-sea hydrothermal mounds by deep-learning based domain adaptation- ABYSSES) is a collaborative project between Ifremer (French Institute for Sea exploitation), CERV (Centre for Virtual Reality), IMT-Atlantique and ENIB, France. Its goal consists in the implementation of new digital tools in order to accelerate our ability to map, at high resolution, and over large spatial areas, the biological, environmental and topography of the seabed. The development of such tools will increase our ability to explore deep benthic ecosystems and therefore increase the acquisition of new knowledge in these environments.
-- Objectives --
The project will explore the extent to which visual characteristics of hydrothermal ecosystems are shared among other visual domains for which the availability of annotated data is substantial. The proliferation of annotated ground truth data in multiple and diverse domains allows to compensate the lack of data for a new domain through its affinity with existing ones. Research in the domain known as transfer learning concerns the family of methods that allow to emerge such affinities in an unsupervised manner. In this context, we are interested in the development of methods belonging to the family of “transductive transfer learning” or “unsupervised domain adaptation”. The objective will be thus to establish the affinity of hydrothermal ecosystems in correspondence with terrestrial surfaces.
(c) GdR 720 ISIS - CNRS - 2011-2020.