Using Contrastive Learning and Pseudolabels to Learn Representations for Retail Product Image Classification

Muktabh Mayank Srivastava

2022

Abstract

Retail product Image classification problems are often few shot classification problems, given retail product classes cannot have the type of variations across images like a cat or dog or tree could have. Previous works have shown different methods to finetune Convolutional Neural Networks to achieve better classification accuracy on such datasets. In this work, we try to address the problem statement : Can we pretrain a Convolutional Neural Network backbone which yields good enough representations for retail product images, so that training a simple logistic regression on these representations gives us good classifiers ? We use contrastive learning and pseudolabel based noisy student training to learn representations that get accuracy in order of the effort of finetuning the entire Convnet backbone for retail product image classification.

Paper Citation

in Harvard Style

Srivastava M. (2022). Using Contrastive Learning and Pseudolabels to Learn Representations for Retail Product Image Classification. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 659-663. DOI: 10.5220/0010911000003124

in Bibtex Style

@conference{visapp22,
author={Muktabh Mayank Srivastava},
title={Using Contrastive Learning and Pseudolabels to Learn Representations for Retail Product Image Classification},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP},
year={2022},
pages={659-663},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010911000003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP
TI - Using Contrastive Learning and Pseudolabels to Learn Representations for Retail Product Image Classification
SN - 978-989-758-555-5
AU - Srivastava M.
PY - 2022
SP - 659
EP - 663
DO - 10.5220/0010911000003124
PB - SciTePress