Avancerad sökning
Visar resultat 1 - 5 av 34 avhandlingar som matchar ovanstående sökkriterier.
1. End-to-End Learning of Deep Structured Models for Semantic Segmentation
Sammanfattning : The task of semantic segmentation aims at understanding an image at a pixel level. This means assigning a label to each pixel of an image, describing the object it is depicting. LÄS MER
2. Learning Spatiotemporal Features in Low-Data and Fine-Grained Action Recognition with an Application to Equine Pain Behavior
Sammanfattning : Recognition of pain in animals is important because pain compromises animal welfare and can be a manifestation of disease. This is a difficult task for veterinarians and caretakers, partly because horses, being prey animals, display subtle pain behavior, and because they cannot verbalize their pain. LÄS MER
3. Representation learning for natural language
Sammanfattning : Artificial neural networks have obtained astonishing results in a diverse number of tasks. One of the reasons for the success is their ability to learn the whole task at once (endto-end learning), including the representations for data. LÄS MER
4. Data-Efficient Learning of Semantic Segmentation
Sammanfattning : Semantic segmentation is a fundamental problem in visual perception with a wide range of applications ranging from robotics to autonomous vehicles, and recent approaches based on deep learning have achieved excellent performance. However, to train such systems there is in general a need for very large datasets of annotated images. LÄS MER
5. Self-supervised Representation Learning for Visual Domains Beyond Natural Scenes
Sammanfattning : This thesis investigates the possibility of efficiently adapting self-supervised representation learning on visual domains beyond natural scenes, e.g., medical imagining and non-RGB sensory images. LÄS MER