Essays about: "Self-Supervised Learning"
Showing result 11 - 15 of 49 essays containing the words Self-Supervised Learning.
-
11. Self-supervised pre-training of an attention-based model for 3D medical image segmentation
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Accurate segmentation of anatomical structures is crucial for radiation therapy in cancer treatment. Deep learning methods have been demonstrated effective for segmentation of 3D medical images, establishing the current standard. However, they require large amounts of labelled data and suffer from reduced performance on domain shift. READ MORE
-
12. Federated Self-supervised Learning in Computer Vision
University essay from Uppsala universitet/Institutionen för informationsteknologiAbstract : With an ever-increasing amount of available image data, self-supervised learning (SSL) circumvents the necessity for annotations in traditional supervised learning methods. SSL methods such as SimSiam have shown excellent results on popular benchmark datasets, even outperforming supervised methods. READ MORE
-
13. Messing With The Gap: On The Modality Gap Phenomenon In Multimodal Contrastive Representation Learning
University essay from Uppsala universitet/Industriell teknikAbstract : In machine learning, a sub-field of computer science, a two-tower architecture model is a specialised type of neural network model that encodes paired data from different modalities (like text and images, sound and video, or proteomics and gene expression profiles) into a shared latent representation space. However, when training these models using a specific contrastive loss function, known as the multimodalinfoNCE loss, seems to often lead to a unique geometric phenomenon known as the modality gap. READ MORE
-
14. Error detection in blood work : Acomparison of self-supervised deep learning-based models
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Errors in medical testing may cause serious problems that has the potential to severely hurt patients. There are many machine learning methods to discover such errors. However, due to the rarity of errors, it is difficult to collect enough examples to learn from them. It is therefore important to focus on methods that do not require human labeling. READ MORE
-
15. Aerial View Image-Goal Localization with Reinforcement Learning
University essay from Lunds universitet/Matematik LTHAbstract : With an increased amount and availability of unmanned aerial vehicles (UAVs) and other remote sensing devices (e.g. satellites) we have recently seen an explosion in computer vision methodologies tailored towards processing and understanding aerial view data. READ MORE
