Sökning: "Triplet-förlust"

Hittade 1 uppsats innehållade ordet Triplet-förlust.

  1. 1. Improving Zero-Shot Learning via Distribution Embeddings

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Vivek Chalumuri; [2020]
    Nyckelord :Zero-Shot Learning ZSL ; Generalized Zero-Shot Learning GZSL ; Image Classification; Metric Learning; Distribution Embeddings; Triplet Loss; Zero-shot lärande; Generaliserat zero-shot-lärande; Bildklassificering; Metrisk inlärning; Distribution inbäddningar; Triplet-förlust;

    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