Training a Custom CNN on Five Heterogeneous Image Datasets

• URL: http://arxiv.org/abs/2601.04727v1
• Date: Thu, 08 Jan 2026 08:44:17 GMT
• Title: Training a Custom CNN on Five Heterogeneous Image Datasets
• Authors: Anika Tabassum, Tasnuva Mahazabin Tuba, Nafisa Naznin,
• Abstract summary: This study investigates the effectiveness of CNN-based architectures across five datasets spanning agricultural and urban domains.<n>These datasets introduce varying challenges, including differences in illumination, resolution, environmental complexity, and class imbalance.<n>We evaluate a lightweight, task-specific custom CNN alongside established deep architectures, including ResNet-18 and VGG-16, trained both from scratch and using transfer learning.
• Score: 1.4583375893645076
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning has transformed visual data analysis, with Convolutional Neural Networks (CNNs) becoming highly effective in learning meaningful feature representations directly from images. Unlike traditional manual feature engineering methods, CNNs automatically extract hierarchical visual patterns, enabling strong performance across diverse real-world contexts. This study investigates the effectiveness of CNN-based architectures across five heterogeneous datasets spanning agricultural and urban domains: mango variety classification, paddy variety identification, road surface condition assessment, auto-rickshaw detection, and footpath encroachment monitoring. These datasets introduce varying challenges, including differences in illumination, resolution, environmental complexity, and class imbalance, necessitating adaptable and robust learning models. We evaluate a lightweight, task-specific custom CNN alongside established deep architectures, including ResNet-18 and VGG-16, trained both from scratch and using transfer learning. Through systematic preprocessing, augmentation, and controlled experimentation, we analyze how architectural complexity, model depth, and pre-training influence convergence, generalization, and performance across datasets of differing scale and difficulty. The key contributions of this work are: (1) the development of an efficient custom CNN that achieves competitive performance across multiple application domains, and (2) a comprehensive comparative analysis highlighting when transfer learning and deep architectures provide substantial advantages, particularly in data-constrained environments. These findings offer practical insights for deploying deep learning models in resource-limited yet high-impact real-world visual classification tasks.

Related papers

• Reliable Deep Learning for Small-Scale Classifications: Experiments on Real-World Image Datasets from Bangladesh [1.0639605996067536]
  We evaluate a compact CNN across five publicly available, real-world image datasets from Bangladesh.<n>The network demonstrates high classification accuracy, efficient convergence, and low computational overhead.
  arXiv  Detail & Related papers  (2026-01-17T05:15:22Z)
• Evolving CNN Architectures: From Custom Designs to Deep Residual Models for Diverse Image Classification and Detection Tasks [0.9023847175654603]
  This paper presents a comparative study of a custom convolutional neural network (CNN) architecture against widely used pretrained and transfer learning CNN models.<n>The datasets span binary classification, fine-grained multiclass recognition, and object detection scenarios.<n>We analyze how architectural factors, such as network depth, residual connections, and feature extraction strategies, influence classification and localization performance.
  arXiv  Detail & Related papers  (2026-01-03T07:45:08Z)
• A Comparative Study of Vision Transformers and CNNs for Few-Shot Rigid Transformation and Fundamental Matrix Estimation [3.5684665108045377]
  Vision-transformers (ViTs) and large-scale convolution-neural-networks (CNNs) have reshaped computer vision through pretrained feature representations.<n>This work considers two such tasks: 1) estimating 2D rigid transformations between pairs of images and 2) predicting the fundamental matrix for stereo image pairs.<n> Empirical comparative analysis shows that, similar to training from scratch, ViTs outperform CNNs during refinement in large downstream-data scenarios.
  arXiv  Detail & Related papers  (2025-10-06T13:18:27Z)
• Underlying Semantic Diffusion for Effective and Efficient In-Context Learning [113.4003355229632]
  Underlying Semantic Diffusion (US-Diffusion) is an enhanced diffusion model that boosts underlying semantics learning, computational efficiency, and in-context learning capabilities.<n>We present a Feedback-Aided Learning (FAL) framework, which leverages feedback signals to guide the model in capturing semantic details.<n>We also propose a plug-and-play Efficient Sampling Strategy (ESS) for dense sampling at time steps with high-noise levels.
  arXiv  Detail & Related papers  (2025-03-06T03:06:22Z)
• Enhanced Convolutional Neural Networks for Improved Image Classification [0.40964539027092917]
  CIFAR-10 is a widely used benchmark to evaluate the performance of classification models on small-scale, multi-class datasets.<n>We propose an enhanced CNN architecture that integrates deeper convolutional blocks, batch normalization, and dropout regularization to achieve superior performance.
  arXiv  Detail & Related papers  (2025-02-02T04:32:25Z)
• Unveiling Backbone Effects in CLIP: Exploring Representational Synergies and Variances [49.631908848868505]
  Contrastive Language-Image Pretraining (CLIP) stands out as a prominent method for image representation learning. We investigate the differences in CLIP performance among various neural architectures. We propose a simple, yet effective approach to combine predictions from multiple backbones, leading to a notable performance boost of up to 6.34%.
  arXiv  Detail & Related papers  (2023-12-22T03:01:41Z)
• Homological Convolutional Neural Networks [4.615338063719135]
  We propose a novel deep learning architecture that exploits the data structural organization through topologically constrained network representations. We test our model on 18 benchmark datasets against 5 classic machine learning and 3 deep learning models.
  arXiv  Detail & Related papers  (2023-08-26T08:48:51Z)
• Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning [54.67880602409801]
  In this paper, we study the problem of pre-training world models with abundant in-the-wild videos for efficient learning of visual control tasks. We introduce Contextualized World Models (ContextWM) that explicitly separate context and dynamics modeling. Our experiments show that in-the-wild video pre-training equipped with ContextWM can significantly improve the sample efficiency of model-based reinforcement learning.
  arXiv  Detail & Related papers  (2023-05-29T14:29:12Z)
• CHALLENGER: Training with Attribution Maps [63.736435657236505]
  We show that utilizing attribution maps for training neural networks can improve regularization of models and thus increase performance. In particular, we show that our generic domain-independent approach yields state-of-the-art results in vision, natural language processing and on time series tasks.
  arXiv  Detail & Related papers  (2022-05-30T13:34:46Z)
• Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition [77.95361323613147]
  Current state-of-the-art visual recognition systems rely on pretraining a neural network on a large-scale dataset and finetuning the network weights on a smaller dataset. In this work, we prove that dynamically adapting network architectures tailored for each domain task along with weight finetuning benefits in both efficiency and effectiveness. Our method can be easily generalized to an unsupervised paradigm by replacing supernet training with self-supervised learning in the source domain tasks and performing linear evaluation in the downstream tasks.
  arXiv  Detail & Related papers  (2021-03-31T08:15:17Z)
• Neural networks adapting to datasets: learning network size and topology [77.34726150561087]
  We introduce a flexible setup allowing for a neural network to learn both its size and topology during the course of a gradient-based training. The resulting network has the structure of a graph tailored to the particular learning task and dataset.
  arXiv  Detail & Related papers  (2020-06-22T12:46:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.