← Search

Angelique Loesch

2 accepted papers

2023

Proposal-Contrastive Pretraining for Object Detection from Fewer Data

ICLR 2023top-25%

The use of pretrained deep neural networks represents an attractive way to achieve strong results with few data available. When specialized in dense problems such as object detection, learning local rather than global information in images has proven to be more efficient. However, for unsupervised p…

Cited by 3SourcePDFScholar
2015

Generic edgelet-based tracking of 3D objects in real-time

IROS 2015poster

This paper addresses the challenging issue of real-time camera localization relative to any object that have texture or not, sharp edges or occluding contours. 3D contour points, dynamically extracted from a CAD model by Analysis-by-Synthesis on the graphics hardware, are combined with a keyframe-ba…

Cited by 16SourceScholar