Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.01099 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909980907536384 |
|---|---|
| author | Hasan, Mahmudul Hossain, Mabsur Fatin Bin |
| author_facet | Hasan, Mahmudul Hossain, Mabsur Fatin Bin |
| contents | This paper presents a comparative study of a custom convolutional neural network (CNN) architecture against widely used pretrained and transfer learning CNN models across five real-world image datasets. The datasets span binary classification, fine-grained multiclass recognition, and object detection scenarios. We analyze how architectural factors, such as network depth, residual connections, and feature extraction strategies, influence classification and localization performance. The results show that deeper CNN architectures provide substantial performance gains on fine-grained multiclass datasets, while lightweight pretrained and transfer learning models remain highly effective for simpler binary classification tasks. Additionally, we extend the proposed architecture to an object detection setting, demonstrating its adaptability in identifying unauthorized auto-rickshaws in real-world traffic scenes. Building upon a systematic analysis of custom CNN architectures alongside pretrained and transfer learning models, this study provides practical guidance for selecting suitable network designs based on task complexity and resource constraints. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_01099 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Evolving CNN Architectures: From Custom Designs to Deep Residual Models for Diverse Image Classification and Detection Tasks Hasan, Mahmudul Hossain, Mabsur Fatin Bin Computer Vision and Pattern Recognition Artificial Intelligence This paper presents a comparative study of a custom convolutional neural network (CNN) architecture against widely used pretrained and transfer learning CNN models across five real-world image datasets. The datasets span binary classification, fine-grained multiclass recognition, and object detection scenarios. We analyze how architectural factors, such as network depth, residual connections, and feature extraction strategies, influence classification and localization performance. The results show that deeper CNN architectures provide substantial performance gains on fine-grained multiclass datasets, while lightweight pretrained and transfer learning models remain highly effective for simpler binary classification tasks. Additionally, we extend the proposed architecture to an object detection setting, demonstrating its adaptability in identifying unauthorized auto-rickshaws in real-world traffic scenes. Building upon a systematic analysis of custom CNN architectures alongside pretrained and transfer learning models, this study provides practical guidance for selecting suitable network designs based on task complexity and resource constraints. |
| title | Evolving CNN Architectures: From Custom Designs to Deep Residual Models for Diverse Image Classification and Detection Tasks |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2601.01099 |