CNN-Transformer Fusion for Indonesian Traditional Cake Recognition: An EfficientNet-ViT Approach with Grad-CAM Explainability
IJNMT (International Journal of New Media Technology) · 30.06.2026 · 13 (1) · 113-119
DOI: 10.31937/ijnmt.v13i1.4775 ↗Kurz gefasst
Fachartikel in der Zeitschrift IJNMT (International Journal of New Media Technology), online erschienen am 30.06.2026. Verfasst von Tasya Yustira und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
Visual recognition of Indonesian traditional confectionery is an underexplored problem in deep learning research, partly due to high inter-class visual ambiguity and the scarcity of well-curated local food benchmarks. We address this gap by fusing Efficient-Net with a Vision Transformer (ViT) encoder into a unified classification network. The rationale for this pairing is straightforward: EfficientNet’s compound-scaled convolutional stack efficiently encodes low and mid-level texture cues, while the ViT’s self-attention layers then relate those cues across distant image regions-a capability that convolution alone cannot replicate. Post-hoc explainability, is provided through Grad-CAM, which produces class-discriminative spatial maps confirming that activations concentrate on cake surfaces rather than background. We train and evaluate on a publicly available eight-class Kaggle corpus of 1,833 images, applying a two-stage fine-tuning regimen totaling 25 epochs. The resulting system attains 94.37% accuracy, 94.57% precision, 94.37% recall, and 94.31% F1 on the reserved test split. Beyond the metrics, the Grad-CAM evidence suggests the network learns genuinely food-discriminative features, lending credibility to deployment in culinary archiving and nutrition-monitoring applications. Index Terms-deep learning; EfficientNet; food image classification; Grad-CAM; Vision Transformer
Zitieren
APA
Yustira, T., & Sunge, A. S. (2026). CNN-Transformer Fusion for Indonesian Traditional Cake Recognition: An EfficientNet-ViT Approach with Grad-CAM Explainability. IJNMT (International Journal of New Media Technology), 13(1), 113-119. https://doi.org/10.31937/ijnmt.v13i1.4775
Vancouver
Yustira T, Sunge AS. CNN-Transformer Fusion for Indonesian Traditional Cake Recognition: An EfficientNet-ViT Approach with Grad-CAM Explainability. IJNMT (International Journal of New Media Technology). 2026;13(1):113-119. doi:10.31937/ijnmt.v13i1.4775
BibTeX
@article{Yustira2026,
author = {Yustira, Tasya and Sunge, Aswan Supriyadi},
title = {CNN-Transformer Fusion for Indonesian Traditional Cake Recognition: An EfficientNet-ViT Approach with Grad-CAM Explainability},
journal = {IJNMT (International Journal of New Media Technology)},
year = {2026},
volume = {13},
number = {1},
pages = {113--119},
doi = {10.31937/ijnmt.v13i1.4775}
}
EUVIMED