@misc{10481/106865,
year = {2025},
month = {7},
url = {https://hdl.handle.net/10481/106865},
abstract = {Generalising deep-learning models to perform well on unseen data domains with minimal retraining remains a significant challenge in computer vision. Even when the target
task—such as quantifying the number of elements in an image—stays the same, data quality, shape, or form variations can deviate from the training conditions, often necessitating
manual intervention. As a real-world industry problem, we aim to automate stock level
estimation in retail cabinets. As technology advances, new cabinet models with varying
shapes emerge alongside new camera types. This evolving scenario poses a substantial
obstacle to deploying long-term, scalable solutions. To surmount the challenge of generalising to new cabinet models and cameras with minimal amounts of sample images,
this research introduces a new solution. This paper proposes a novel ensemble model
that combines DenseNet-201 and Vision Transformer (ViT-B/8) architectures to achieve
generalisation in stock-level classification. The novelty aspect of our solution comes from
the fact that we combine a transformer with a DenseNet model in order to capture both the
local, hierarchical details and the long-range dependencies within the images, improving
generalisation accuracy with less data. Key contributions include (i) a novel DenseNet-201
+ ViT-B/8 feature-level fusion, (ii) an adaptation workflow that needs only two images
per class, (iii) a balanced layer-unfreezing schedule, (iv) a publicly described domain-shift
benchmark, and (v) a 47 pp accuracy gain over four standard few-shot baselines. Our
approach leverages fine-tuning techniques to adapt two pre-trained models to the new
retail cabinets (i.e., standing or horizontal) and camera types using only two images per
class. Experimental results demonstrate that our method achieves high accuracy rates
of 91% on new cabinets with the same camera and 89% on new cabinets with different
cameras, significantly outperforming standard few-shot learning methods.},
organization = {Innovate UK and Unilever PLC (grant number KTP13113)},
organization = {European Union Next Generation - Ministry for Digital Transformation and the Civil Service (TSI-100927-2023-1 Project)},
publisher = {Rahi, B.; Sagmanli, D.; Oppong, F.; Pekaslan, D.; Triguero, I. Generalising Stock Detection in Retail Cabinets with Minimal Data Using a DenseNet and Vision Transformer Ensemble. Mach. Learn. Knowl. Extr. 2025, 7, 66. https://doi.org/10.3390/make7030066},
keywords = {ensemble model},
keywords = {Image classification},
keywords = {DenseNet-20},
title = {Generalising Stock Detection in Retail Cabinets with Minimal Data Using a DenseNet and Vision Transformer Ensemble},
doi = {10.3390/make7030066},
author = {Rahi, Babak and Sagmanli, Deniz and Oppong, Felix and Pekaslan, Direnc and Triguero, Isaac},
}