mlsanityData to 14 Oct 2026

Online Anchor-based Training for Image Classification Tasks

arXiv 2406.12662 ↗First posted 18 Jun 2024cs.CVcited by 0

Not on the map. Why?

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.

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

16 of 29 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2017Mask R-CNNcited by 7,277
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  6. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  7. 2016Wide Residual Networkscited by 3,070
  8. 2019When Does Label Smoothing Help?cited by 988
  9. 2021Going deeper with Image Transformerscited by 764
  10. 2021A Survey of Visual Transformerscited by 117
  11. 2020Delving Deep into Label Smoothingcited by 94
  12. 2017Regularization for Deep Learning: A Taxonomycited by 91
4 more
  1. 2017Evolving Deep Convolutional Neural Networks for Image Classificationcited by 55
  2. 2022Discover and Mitigate Unknown Biases with Debiasing Alternate Networkscited by 47
  3. 2020AnchorFace: An Anchor-based Facial Landmark Detector Across Large Posescited by 10
  4. 2021Efficient training of lightweight neural networks using Online Self-Acquired Knowledge Distillationcited by 1

Built on by

Not cited yet.