Essays about: "Metrisk Inlärning"
Showing result 1 - 5 of 6 essays containing the words Metrisk Inlärning.
-
1. Multi-modal Models for Product Similarity : Comparative evaluation of unimodal and multi-modal architectures for product similarity prediction and product retrieval
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : 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. READ MORE
-
2. Distance preserving Fermat VAE
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : 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. READ MORE
-
3. Attribute Embedding for Variational Auto-Encoders : Regularization derived from triplet loss
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : 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. READ MORE
-
4. Pushing the boundary of Semantic Image Segmentation
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : 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. READ MORE
-
5. Improving Zero-Shot Learning via Distribution Embeddings
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : 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. READ MORE