Источник
IWANN
Дата публикации
21.08.2021
Авторы
Илья Макаров Борис Цейтлин
Поделиться

Hotel Recognition via Latent Image Embeddings

Аннотация

We approach the problem of hotel recognition with deep metric learning. We overview the existing approaches and propose a modification to Contrastive loss called Contrastive-Triplet loss. We construct a robust pipeline for benchmarking metric learning models and perform experiments on Hotels-50K and CUB200 datasets. Contrastive-Triplet loss is shown to achieve better retrieval on Hotels-50k.

Присоединяйтесь к AIRI в соцсетях