paper-with-me

Papers

Reliable Deep Learning for Small-Scale Classifications: Experiments on Real-World Image Datasets from Bangladesh

2026-01-17 · Alfe Suny, MD Sakib Ul Islam, Md. Imran Hossain arxiv

Convolutional neural networks (CNNs) have achieved state-of-the-art performance in image recognition tasks but often involve complex architectures that may overfit on small datasets. In this study, we evaluate a compact CNN across five publicly available, real-world image datasets from Bangladesh, including urban encroachment, vehicle detection, road damage, and agricultural crops. The network demonstrates high classification accuracy, efficient convergence, and low computational overhead. Quantitative metrics and saliency analyses indicate that the model effectively captures discriminative features and generalizes robustly across diverse scenarios, highlighting the suitability of streamlined CNN architectures for small-class image classification tasks.

📄 PDF Abstract BibTeX arXiv:2601.11911

Code (0)

등록된 구현이 없습니다.

Tasks

Image Classification

Similar Papers 제목 키워드 기반

The CM Algorithm for the Maximum Mutual Information Classifications of Unseen Instances

2019-01-28 · Chenguang Lu

The Maximum Mutual Information (MMI) criterion is different from the Least Error Rate (LER) criterion. It can reduce failing to report small probability events. This paper introduces the Channels Matching (CM) algorithm …

Filtered-ViT: A Robust Defense Against Multiple Adversarial Patch Attacks

2025-11-11 · Aja Khanal, Ahmed Faid, Apurva Narayan arxiv

Deep learning vision systems are increasingly deployed in safety-critical domains such as healthcare, yet they remain vulnerable to small adversarial patches that can trigger misclassifications. Most existing defenses as…

Deep-ICE: The first globally optimal algorithm for empirical risk minimization of two-layer maxout and ReLU networks

2025-05-09 · Xi He, Yi Miao, Max A. Little

This paper introduces the first globally optimal algorithm for the empirical risk minimization problem of two-layer maxout and ReLU networks, i.e., minimizing the number of misclassifications. The algorithm has a worst-c…

Superior Scoring Rules for Probabilistic Evaluation of Single-Label Multi-Class Classification Tasks

2024-07-25 · Rouhollah Ahmadian, Mehdi Ghatee, Johan Wahlström

This study introduces novel superior scoring rules called Penalized Brier Score (PBS) and Penalized Logarithmic Loss (PLL) to improve model evaluation for probabilistic classification. Traditional scoring rules like Brie…

Model OptimizationModel SelectionMulti-class Classificationscoring rule+1

Detecting Adversarial Examples and Other Misclassifications in Neural Networks by Introspection

2019-05-22 · Jonathan Aigrain, Marcin Detyniecki

Despite having excellent performances for a wide variety of tasks, modern neural networks are unable to provide a reliable confidence value allowing to detect misclassifications. This limitation is at the heart of what i…