# Online Anchor-based Training for Image Classification Tasks

arXiv: https://arxiv.org/abs/2406.12662 · HTML: https://mlsanity.com/paper/2406.12662/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 29 references that are in the map.
- First posted on arXiv 18 Jun 2024.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [A Survey of Visual Transformers](https://mlsanity.com/paper/2111.06091/) (2021)
- [Delving Deep into Label Smoothing](https://mlsanity.com/paper/2011.12562/) (2020)
- [Regularization for Deep Learning: A Taxonomy](https://mlsanity.com/paper/1710.10686/) (2017)
- [Evolving Deep Convolutional Neural Networks for Image Classification](https://mlsanity.com/paper/1710.10741/) (2017)
- [Discover and Mitigate Unknown Biases with Debiasing Alternate Networks](https://mlsanity.com/paper/2207.10077/) (2022)
- [AnchorFace: An Anchor-based Facial Landmark Detector Across Large Poses](https://mlsanity.com/paper/2007.03221/) (2020)
- [Efficient training of lightweight neural networks using Online Self-Acquired Knowledge Distillation](https://mlsanity.com/paper/2108.11798/) (2021)

## Abstract (arXiv)

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 textitOnline 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.