# Online Anchor-based Training for Image Classification Tasks

Source: [Online Anchor-based Training for Image Classification Tasks](<https://www.sota2.com/research/paper/68fa73ab1e209131cea5dcfa>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:54:13.197Z

Authors: Maria Tzelepi, Vasileios Mezaris

Published: 2024-06-18T14:31:39.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2406.12662>)

[PDF](<https://arxiv.org/pdf/2406.12662.pdf>)