English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this thesis, we develop theoretical, algorithmic and experimentalcontributions for Machine Learning with limited labels, and more specificallyfor the tasks of Image Classification and Object Detection in Computer Vision.In a first contribution, we are interested in bridging the gap between theoryand practice for popular Meta-Learning algorithms used in Few-ShotClassification. We make connections to Multi-Task Representation Learning,which benefits from solid theoretical foundations, to verify the bestconditions for a more efficient meta-learning. Then, to leverage unlabeled datawhen training object detectors based on the Transformer architecture, wepropose both an unsupervised pretraining and a semi-supervised learning methodin two other separate contributions. For pretraining, we improve ContrastiveLearning for object detectors by introducing the localization information.Finally, our semi-supervised method is the first tailored to transformer-baseddetectors.

Towards Few-Annotation Learning in Computer Vision: Application to Image Classification and Object Detection tasks