PhD position in Few-shot learning: Application to object detection and semantic instance segmentation CEA Tech Department of Computer Science and Software France

JOB DETAILS
Title: PhD position - Few-shot learning: Application to object detection and semantic instance segmentation
Employer: CEA Tech
Job location: 17 rue des martyrs, F-38054 Grenoble
Published: July 27, 2019
Application deadline: October 31, 2019
Job types: PhD
Fields: Informatics, Information Science, Algorithms, Statistics, Artificial Intelligence, Artificial Neural Network, Computer and Society, Computer Architecture, Computer Communications (Networks) and 26 more.


JOB DESCRIPTION

SL-DRT-19-1084

RESEARCH FIELD
Computer science and software

 

ABSTRACT
Nowadays, many computer vision tasks are successfully managed by deep learning models. Those include, for example, object detection and recognition, image classification, person, gesture, action or activity recognition... which are useful in many fields of application (video-surveillance, autonomous driving, robotics, industry 4.0, medical image analysis, active assisted living, etc.). The drawback of these deep neural networks-based approaches is that they require a huge amount of annotated data during their supervised training. On the one hand, manual data annotation is a tedious and expensive task. On the other hand, data can also be rare or difficult to gather for some reasons, including privacy, safety, or ethics. It is therefore essential to design methods that learn from very few annotated samples of data. The challenge of few-shot learning is then to approach, even surpass, human ability to learn and generalize from few examples. The objective of this thesis is to propose novel methods that optimize the model ability to rapidly handle new tasks, including detecting, segmenting and recognizing new object classes. A comparative study between state-of-the-art and developed methods will be carried out on many datasets in order to quantify performance improvements, dependence on number 0of samples, as well as generalization ability relative to types of data.

 

LOCATION
Département Intelligence Ambiante et Systèmes Interactifs (LIST)

Vision & Ingénierie des Contenus (SAC)

Saclay

CONTACT PERSON
AUDIGIER Romaric

CEA

DRT/DIASI//LVIC/SAC

CEA SACLAYDIASI/LVICBat. 861 - PC 17391191 Gif-sur-Yvette

Phone number: 01 69 08 01 06

Email: romaric.audigier@cea.fr

UNIVERSITY / GRADUATE SCHOOL
Saint-Etienne

Sciences, Ingénierie, Santé (EDSIS)

FIND OUT MORE
http://www-list.cea.fr/

START DATE
Start date on 01-10-2019

THESIS SUPERVISOR
HABRARD Amaury

Université Jean Monnet, Saint-Etienne

Laboratoire Hubert Curien UMR CNRS 5516

Laboratoire Hubert Curien18 rue du Professeur Benoît Lauras42000 Saint-EtienneFRANCE

Phone number: +33 4 69 66 32 64

Email: amaury.habrard@univ-st-etienne.fr

« The age limit is 26 years for PhD offers and 30 years old for post-doc offers. »


If you apply for this position please say you saw it on Computeroxy

Apply

All Jobs

FACEBOOK
TWITTER
LINKEDIN
GOOGLE
https://computeroxy.com/phd-position-in-few-shot-learning-application-to-object-detection-and-semantic-instance-segmentation,i8118.html">

Harvard University Academic Positions

Kuwait University Current Faculty Openings

Osaka University Academic Opportunities

Purdue University Job Postings for Faculty Positions

Texas Tech University Faculty Openings

Tsinghua University Job Postings

University of Cambridge Job Openings

University of Geneva Faculty Opportunities

University of New South Wales Job Openings

University of Nottingham Research Positions

University of Oslo Academic Jobs

University of Saskatchewan Faculty Positions

University of Southampton Research Vacancies

University of Tokyo Current Academic Vacancies

University of Toronto Open Faculty Positions