Online Anchor-based Training for Image Classification Tasks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tzelepi, Maria, Mezaris, Vasileios
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910493382279168
author Tzelepi, Maria
Mezaris, Vasileios
author_facet Tzelepi, Maria
Mezaris, Vasileios
contents In this paper, we aim to improve the performance of a deep learning model towards image classification tasks, proposing a novel anchor-based training methodology, named \textit{Online Anchor-based Training} (OAT). The OAT method, guided by the insights provided in the anchor-based object detection methodologies, instead of learning directly the class labels, proposes to train a model to learn percentage changes of the class labels with respect to defined anchors. We define as anchors the batch centers at the output of the model. Then, during the test phase, the predictions are converted back to the original class label space, and the performance is evaluated. The effectiveness of the OAT method is validated on four datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2406_12662
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Online Anchor-based Training for Image Classification Tasks
Tzelepi, Maria
Mezaris, Vasileios
Computer Vision and Pattern Recognition
In this paper, we aim to improve the performance of a deep learning model towards image classification tasks, proposing a novel anchor-based training methodology, named \textit{Online Anchor-based Training} (OAT). The OAT method, guided by the insights provided in the anchor-based object detection methodologies, instead of learning directly the class labels, proposes to train a model to learn percentage changes of the class labels with respect to defined anchors. We define as anchors the batch centers at the output of the model. Then, during the test phase, the predictions are converted back to the original class label space, and the performance is evaluated. The effectiveness of the OAT method is validated on four datasets.
title Online Anchor-based Training for Image Classification Tasks
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.12662