Experimental Comparison of Light-Weight and Deep CNN Models Across Diverse Datasets
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915712623181824 |
|---|---|
| author | Papon, Md. Hefzul Hossain Rabby, Shadman |
| author_facet | Papon, Md. Hefzul Hossain Rabby, Shadman |
| contents | Our results reveal that a well-regularized shallow architecture can serve as a highly competitive baseline across heterogeneous domains - from smart-city surveillance to agricultural variety classification - without requiring large GPUs or specialized pre-trained models. This work establishes a unified, reproducible benchmark for multiple Bangladeshi vision datasets and highlights the practical value of lightweight CNNs for real-world deployment in low-resource settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03463 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Experimental Comparison of Light-Weight and Deep CNN Models Across Diverse Datasets Papon, Md. Hefzul Hossain Rabby, Shadman Computer Vision and Pattern Recognition Machine Learning Our results reveal that a well-regularized shallow architecture can serve as a highly competitive baseline across heterogeneous domains - from smart-city surveillance to agricultural variety classification - without requiring large GPUs or specialized pre-trained models. This work establishes a unified, reproducible benchmark for multiple Bangladeshi vision datasets and highlights the practical value of lightweight CNNs for real-world deployment in low-resource settings. |
| title | Experimental Comparison of Light-Weight and Deep CNN Models Across Diverse Datasets |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2601.03463 |