Sökning: "Metrisk inlärning"
Visar resultat 1 - 5 av 6 uppsatser innehållade orden Metrisk inlärning.
1. 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
2. Distance preserving Fermat VAE
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Deep neural networks takes their strength in the representations, or features, that they internally build. While these internal encodings help networks performing classification or regression tasks on specific data types, it exists a branch of machine learning that has for only purpose to build these representations. LÄS MER
3. Attribute Embedding for Variational Auto-Encoders : Regularization derived from triplet loss
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Techniques for imposing a structure on the latent space of neural networks have seen much development in recent years. Clustering techniques used for classification have been used to great success, and with this work we hope to bridge the gap between contrastive losses and Generative models. LÄS MER
4. Pushing the boundary of Semantic Image Segmentation
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The state-of-the-art object detection and image classification methods can perform impressively on more than 9k classes. In contrast, the number of classes in semantic segmentation datasets are fairly limited. This is not surprising , when the restrictions caused by the lack of labeled data and high computation demand are considered. LÄS MER
5. Improving Zero-Shot Learning via Distribution Embeddings
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Zero-Shot Learning (ZSL) for image classification aims to recognize images from novel classes for which we have no training examples. A common approach to tackling such a problem is by transferring knowledge from seen to unseen classes using some auxiliary semantic information of class labels in the form of class embeddings. LÄS MER