# Hotel Recognition via Latent Image Embedding

arXiv: https://arxiv.org/abs/2106.08042 · HTML: https://mlsanity.com/paper/2106.08042/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 28 references that are in the map.
- First posted on arXiv 15 Jun 2021.

## Builds on (most cited first, 11 of 11)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning](https://mlsanity.com/paper/1904.06627/) (2019)
- [A Metric Learning Reality Check](https://mlsanity.com/paper/2003.08505/) (2020)
- [No Fuss Distance Metric Learning using Proxies](https://mlsanity.com/paper/1703.07464/) (2017)
- [ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis](https://mlsanity.com/paper/2004.01113/) (2020)
- [Improved Embeddings with Easy Positive Triplet Mining](https://mlsanity.com/paper/1904.04370/) (2019)
- [Attention-based Ensemble for Deep Metric Learning](https://mlsanity.com/paper/1804.00382/) (2018)
- [Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning](https://mlsanity.com/paper/2003.02546/) (2020)
- [Combination of Multiple Global Descriptors for Image Retrieval](https://mlsanity.com/paper/1903.10663/) (2019)
- [Hotels-50K: A Global Hotel Recognition Dataset](https://mlsanity.com/paper/1901.11397/) (2019)

## Built on by (most cited first, 1 of 1)

- [Frame-level Prediction of Facial Expressions, Valence, Arousal and Action Units for Mobile Devices](https://mlsanity.com/paper/2203.13436/) (2022)

## Abstract (arXiv)

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. We open-source our code.