Section: Bilateral Contracts and Grants with Industry

Bilateral Contracts with Industry

Few shot learning for object recognition in aerial images (CIFRE PhD)

Participants : Yannis Avrithis, Yann Lifchitz.

Duration: 3 years, started in March 2018

Partner: Safran

This is a CIFRE PhD thesis project aiming to study architectures and learning techniques most suitable for object recognition from few samples and to validate these approaches on multiple recognition tasks and use-cases related to aerial images.

Incremental dynamic construction of knowledge bases from text mining (CIFRE PhD)

Participants : Guillaume Gravier, Pascale Sébillot, Cyrielle Mallart.

Duration: 3 years, started in Dec. 2018

Partner: Ouest France

In the context of a newspaper, the thesis explores the combination of text mining and knowledge representation techniques to assist the extraction, interpretation and validation of valuable pieces of information from the journal's content so as to incrementally build a full-scale knowledge base. This thesis is in close relation with the iCODA Inria Project Lab, with direct contribution to the project's results.

Embedding heterogeneous data for directory search (CIFRE PhD)

Participants : Guillaume Gravier, Vincent Claveau, François Torregrossa.

Duration: 3 years, started in Dec. 2018

Partner: SoLocal

The thesis aims at learning how to jointly exploit heterogeneous sources of information (e.g., names, activity sector, user profiles, queries, etc.) in the design of neural network embeddings for information retrieval and language understanding. Applications cover natural language query analysis and personalized information retrieval in Pagesjaunes' directory.

Active learning on adaptive representations for object detection in high-resolution imaging (CIFRE PhD)

Participants : Ewa Kijak, Mathieu Laroze.

Duration: 3 years, started in Jun. 2016

Partner: Wipsea

Wipsea is a Rennaise startup, created in 2013 whose core business is image analysis for ecology. WIPSEA helps biologists, Unmanned Aerial Vehicle (UAV) companies and environmental consultants to automatically process automatically captured pictures by proposing image-processing algorithms that detect and characterize all kinds of animals such as dugongs, whales, elephants, and orangutans... The main objective of the thesis is to develop a detection method to optimize the interaction between the expert and the system in order to converge as quickly as possible to an object detection solution adapted to a given task.