Object detectors are important components of intelligent systems such as autonomous vehicles or robots. They are typically obtained with fully-supervised training, which requires large manually annotated datasets whose construction is time-consuming and costly. This thesis studies alternatives to fully-supervised object detection that work with less or even no manual annotation. We focus in the first part of this thesis on the unsupervised object discovery problem, which, given an image collection without manual annotation, aims at identifying pairs of images that contain similar objects and localizing these objects. We discuss two optimization-based approaches(OSD and rOSD), a ranking method (LOD) and a simple seed-growing approach that ex...
Object detection has witnessed significant progress by relying on large, manually annotated datasets...
Hægt að skoða forritunar kóðan í skýrslunni, eða í vefslóðunum sem fylgja.This thesis examines the u...
Supervised learning, the standard paradigm in machine learning, only works well if a sufficiently la...
Object detectors are important components of intelligent systems such as autonomous vehicles or robo...
In this dissertation we address the problem of weakly supervised object detection, wherein the goal ...
International audienceObject detectors trained with weak annotations are affordable alternatives to ...
Efficient detection of multiple object instances is one of the fundamental challenges in computer vi...
International audienceLocalizing objects in image collections without supervision can help to avoid ...
Object detection in images and videos is an important topic in computer vision. In general, a large ...
This thesis concerns the problem of object detection, which is defined as finding all instances of a...
We study the problem of using active learning to reduce annotation effort in training object detecto...
A fundamental challenge in deploying vision-based object detection on a robotic platform is achievin...
Active learning and crowdsourcing are promising ways to efficiently build up training sets for objec...
We address the problem of training Object Detection models using significantly less bounding box ann...
Bilen H., Pedersoli M., Tuytelaars T., ''Weakly supervised object detection with posterior regulariz...
Object detection has witnessed significant progress by relying on large, manually annotated datasets...
Hægt að skoða forritunar kóðan í skýrslunni, eða í vefslóðunum sem fylgja.This thesis examines the u...
Supervised learning, the standard paradigm in machine learning, only works well if a sufficiently la...
Object detectors are important components of intelligent systems such as autonomous vehicles or robo...
In this dissertation we address the problem of weakly supervised object detection, wherein the goal ...
International audienceObject detectors trained with weak annotations are affordable alternatives to ...
Efficient detection of multiple object instances is one of the fundamental challenges in computer vi...
International audienceLocalizing objects in image collections without supervision can help to avoid ...
Object detection in images and videos is an important topic in computer vision. In general, a large ...
This thesis concerns the problem of object detection, which is defined as finding all instances of a...
We study the problem of using active learning to reduce annotation effort in training object detecto...
A fundamental challenge in deploying vision-based object detection on a robotic platform is achievin...
Active learning and crowdsourcing are promising ways to efficiently build up training sets for objec...
We address the problem of training Object Detection models using significantly less bounding box ann...
Bilen H., Pedersoli M., Tuytelaars T., ''Weakly supervised object detection with posterior regulariz...
Object detection has witnessed significant progress by relying on large, manually annotated datasets...
Hægt að skoða forritunar kóðan í skýrslunni, eða í vefslóðunum sem fylgja.This thesis examines the u...
Supervised learning, the standard paradigm in machine learning, only works well if a sufficiently la...