Sökning: "end-to-end learning"

Visar resultat 1 - 5 av 35 avhandlingar innehållade orden end-to-end learning.

1. 1. End-to-End Learning of Deep Structured Models for Semantic Segmentation

   Författare :Måns Larsson; Chalmers tekniska högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Semantic segmentation; deep structured models; supervised learning; convolutional neural networks; conditional random fields;

   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

3. 2. Learning Spatiotemporal Features in Low-Data and Fine-Grained Action Recognition with an Application to Equine Pain Behavior

   Författare :Sofia Broomé; Hedvig Kjellström; Efstratios Gavves; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Equine pain; computer vision for animals; deep learning; deep video models; spatiotemporal features; video understanding; action recognition; frame dependency; video data; end-to-end learning; temporal modeling; Datalogi; Computer Science;

   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

4. 3. Representation learning for natural language

   Författare :Olof Mogren; RISE; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; artificial neural networks; artificial intelligence; natural language processing; deep learning; machine learning; summarization; representation learning;

   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

5. 4. Data-Efficient Learning of Semantic Segmentation

   Författare :David Nilsson; Mathematical Imaging Group; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; semantic segmentation; embodied learning; active learning; semantic video segmentation; computer vision; deep learning;

   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

7. 5. Self-supervised Representation Learning for Visual Domains Beyond Natural Scenes

   Författare :Prakash Chandra Chhipa; Marcus Liwicki; Seiichi Uchida; Rajkumar Saini; Josep Lladós; Luleå tekniska universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; self-supervised learning; representation learning; computer vision; learning with few labels; Maskininlärning; Machine Learning;

   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