Fine-Grained ImageNet Classification in the Wild

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lymperaiou, Maria, Thomas, Konstantinos, Stamou, Giorgos
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914781987864576
author Lymperaiou, Maria
Thomas, Konstantinos
Stamou, Giorgos
author_facet Lymperaiou, Maria
Thomas, Konstantinos
Stamou, Giorgos
contents Image classification has been one of the most popular tasks in Deep Learning, seeing an abundance of impressive implementations each year. However, there is a lot of criticism tied to promoting complex architectures that continuously push performance metrics higher and higher. Robustness tests can uncover several vulnerabilities and biases which go unnoticed during the typical model evaluation stage. So far, model robustness under distribution shifts has mainly been examined within carefully curated datasets. Nevertheless, such approaches do not test the real response of classifiers in the wild, e.g. when uncurated web-crawled image data of corresponding classes are provided. In our work, we perform fine-grained classification on closely related categories, which are identified with the help of hierarchical knowledge. Extensive experimentation on a variety of convolutional and transformer-based architectures reveals model robustness in this novel setting. Finally, hierarchical knowledge is again employed to evaluate and explain misclassifications, providing an information-rich evaluation scheme adaptable to any classifier.
format Preprint
id arxiv_https___arxiv_org_abs_2303_02400
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Fine-Grained ImageNet Classification in the Wild
Lymperaiou, Maria
Thomas, Konstantinos
Stamou, Giorgos
Computer Vision and Pattern Recognition
Artificial Intelligence
Image classification has been one of the most popular tasks in Deep Learning, seeing an abundance of impressive implementations each year. However, there is a lot of criticism tied to promoting complex architectures that continuously push performance metrics higher and higher. Robustness tests can uncover several vulnerabilities and biases which go unnoticed during the typical model evaluation stage. So far, model robustness under distribution shifts has mainly been examined within carefully curated datasets. Nevertheless, such approaches do not test the real response of classifiers in the wild, e.g. when uncurated web-crawled image data of corresponding classes are provided. In our work, we perform fine-grained classification on closely related categories, which are identified with the help of hierarchical knowledge. Extensive experimentation on a variety of convolutional and transformer-based architectures reveals model robustness in this novel setting. Finally, hierarchical knowledge is again employed to evaluate and explain misclassifications, providing an information-rich evaluation scheme adaptable to any classifier.
title Fine-Grained ImageNet Classification in the Wild
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2303.02400