RetailKLIP: Finetuning OpenCLIP Backbone Using Metric Learning on a Single GPU for Zero-Shot Retail Product Image Classification

Muktabh Srivastava

2024

Abstract

Retail product or packaged grocery goods images need to classified in various computer vision applications like self checkout stores, supply chain automation and retail execution evaluation. Previous works explore ways to finetune deep models for this purpose. But because of the fact that finetuning a large model or even linear layer for a pretrained backbone requires to run at least a few epochs of gradient descent for every new retail product added in classification range, frequent retrainings are needed in a real world scenario. In this work, we propose finetuning the vision encoder of a CLIP model in a way that its embeddings can be easily used for nearest neighbor based classification, while also getting accuracy close to or exceeding full finetuning. A nearest neighbor based classifier needs no incremental training for new products, thus saving resources and wait time.

Paper Citation

in Harvard Style

Srivastava M. (2024). RetailKLIP: Finetuning OpenCLIP Backbone Using Metric Learning on a Single GPU for Zero-Shot Retail Product Image Classification. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 830-834. DOI: 10.5220/0012576000003660

in Bibtex Style

@conference{visapp24,
author={Muktabh Srivastava},
title={RetailKLIP: Finetuning OpenCLIP Backbone Using Metric Learning on a Single GPU for Zero-Shot Retail Product Image Classification},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2024},
pages={830-834},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012576000003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - RetailKLIP: Finetuning OpenCLIP Backbone Using Metric Learning on a Single GPU for Zero-Shot Retail Product Image Classification
SN - 978-989-758-679-8
AU - Srivastava M.
PY - 2024
SP - 830
EP - 834
DO - 10.5220/0012576000003660
PB - SciTePress