Sökning: "triplet loss"
Visar resultat 1 - 5 av 19 uppsatser innehållade orden triplet loss.
1. Using Machine Learning to Optimize Near-Earth Object Sighting Data at the Golden Ears Observatory
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : This research project focuses on improving Near-Earth Object (NEO) detection using advanced machine learning techniques, particularly Vision Transformers (ViTs). The study addresses challenges such as noise, limited data, and class imbalance. LÄS MER
2. Image generation through feature extraction and learning using a deep learning approach
Master-uppsats, Linnéuniversitetet/Institutionen för datavetenskap och medieteknik (DM)Sammanfattning : With recent advancements, image generation has become more and more possible with the introduction of stronger generative artificial intelligence (AI) models. The idea and ability of generating non-existing images that highly resemble real world images is interesting for many use cases. LÄS MER
3. Multi-modal Models for Product Similarity : Comparative evaluation of unimodal and multi-modal architectures for product similarity prediction and product retrieval
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : With the rapid growth of e-commerce, enabling effective product recommendation systems and improving product search for shoppers plays a crucial role in driving customer satisfaction. Traditional product retrieval approaches have mainly relied on unimodal models focusing on text data. LÄS MER
4. Enhancing person re-identification: leveraging DensePose for improving occlusion handling and generalization
Master-uppsats, Lunds universitet/Matematik LTHSammanfattning : In this master’s thesis we propose a DensePose-based person re-identification (re-ID) machine learning algorithm building upon previous research on this topic. DensePose, a deep neural network that performs human body part segmentation on images, forms the foundation of our approach. LÄS MER
5. GPS-Free UAV Geo-Localization Using a Reference 3D Database
Master-uppsats, Linköpings universitet/Institutionen för systemteknikSammanfattning : The goal of this thesis has been global geolocalization using only visual input and a 3D database for reference. In recent years Convolutional Neural Networks (CNNs) have seen huge success in the task of classifying images. The flattened tensors at the final layers of a CNN can be viewed as vectors describing different input image features. LÄS MER