The ability of deep-learning methods to excel in computer vision highly depends on the amount of annotated data available for training. For some tasks, annotation may be too costly and labor intensive, thus becoming the main obstacle to better accuracy. Algorithms that learn from data automatically, without human supervision, perform substantially worse than their fully-supervised counterparts. Thus, there is a strong motivation to work on effective methods for learning with limited annotations. This thesis proposes to exploit prior knowledge about the task and develops more effective solutions for scene understanding and few-shot image classification.Main challenges of scene understanding include object detection, semantic and instance seg...
Resource de calcul : INSA de Rouen Normandie, cluster de calcul de l'UFR Sciences etTechniques, Le C...
Resource de calcul : INSA de Rouen Normandie, cluster de calcul de l'UFR Sciences etTechniques, Le C...
Neural network models and deep models are one of the leading and state of the art models in machine ...
The ability of deep-learning methods to excel in computer vision highly depends on the amount of ann...
The ability of deep-learning methods to excel in computer vision highly depends on the amount of ann...
The ability of deep-learning methods to excel in computer vision highly depends on the amount of ann...
La capacité des méthodes d'apprentissage profond à exceller en vision par ordinateur dépend fortemen...
Recent development in deep learning have achieved impressive results on image understanding tasks. H...
Recent development in deep learning have achieved impressive results on image understanding tasks. H...
Recent development in deep learning have achieved impressive results on image understanding tasks. H...
Recent development in deep learning have achieved impressive results on image understanding tasks. H...
In this dissertation we address the problem of weakly supervised object detection, wherein the goal ...
In this dissertation we address the problem of weakly supervised object detection, wherein the goal ...
In this dissertation we address the problem of weakly supervised object detection, wherein the goal ...
Resource de calcul : INSA de Rouen Normandie, cluster de calcul de l'UFR Sciences etTechniques, Le C...
Resource de calcul : INSA de Rouen Normandie, cluster de calcul de l'UFR Sciences etTechniques, Le C...
Resource de calcul : INSA de Rouen Normandie, cluster de calcul de l'UFR Sciences etTechniques, Le C...
Neural network models and deep models are one of the leading and state of the art models in machine ...
The ability of deep-learning methods to excel in computer vision highly depends on the amount of ann...
The ability of deep-learning methods to excel in computer vision highly depends on the amount of ann...
The ability of deep-learning methods to excel in computer vision highly depends on the amount of ann...
La capacité des méthodes d'apprentissage profond à exceller en vision par ordinateur dépend fortemen...
Recent development in deep learning have achieved impressive results on image understanding tasks. H...
Recent development in deep learning have achieved impressive results on image understanding tasks. H...
Recent development in deep learning have achieved impressive results on image understanding tasks. H...
Recent development in deep learning have achieved impressive results on image understanding tasks. H...
In this dissertation we address the problem of weakly supervised object detection, wherein the goal ...
In this dissertation we address the problem of weakly supervised object detection, wherein the goal ...
In this dissertation we address the problem of weakly supervised object detection, wherein the goal ...
Resource de calcul : INSA de Rouen Normandie, cluster de calcul de l'UFR Sciences etTechniques, Le C...
Resource de calcul : INSA de Rouen Normandie, cluster de calcul de l'UFR Sciences etTechniques, Le C...
Resource de calcul : INSA de Rouen Normandie, cluster de calcul de l'UFR Sciences etTechniques, Le C...
Neural network models and deep models are one of the leading and state of the art models in machine ...