Portrait de Aarash Feizi

Aarash Feizi

Doctorat - McGill
Superviseur⋅e principal⋅e
Reihaneh Rabbany
Co-supervisor
Adriana Romero Soriano
Sujets de recherche
Apprentissage profond
Réseaux de neurones en graphes
Vision par ordinateur
Site web
Google Scholar
GitHub

Publications

Revisiting Hotels-50K and Hotel-ID
Aarash Feizi
Arantxa Casanova
Adriana Romero Soriano
Reihaneh Rabbany
In this paper, we propose revisited versions for two recent hotel recognition datasets: Hotels-50K and Hotel-ID. The revisited versions prov… (voir plus)ide evaluation setups with different levels of difficulty to better align with the intended real-world application, i.e. countering human trafficking. Real-world scenarios involve hotels and locations that are not captured in the current data sets, therefore it is important to consider evaluation settings where classes are truly unseen. We test this setup using multiple state-of-the-art image retrieval models and show that as expected, the models’ performances decrease as the evaluation gets closer to the real-world unseen settings. The rankings of the best performing models also change across the different evaluation settings, which further motivates using the proposed revisited datasets.
2022-07-20
ArXiv (prépublication)
doi.org
arxiv.org