Theoretical understanding of convolutional neural network: Concepts, architectures, applications, future directions

MM Taye - Computation, 2023‏ - mdpi.com
Convolutional neural networks (CNNs) are one of the main types of neural networks used for
image recognition and classification. CNNs have several uses, some of which are object …

A survey and performance evaluation of deep learning methods for small object detection

Y Liu, P Sun, N Wergeles, Y Shang - Expert Systems with Applications, 2021‏ - Elsevier
In computer vision, significant advances have been made on object detection with the rapid
development of deep convolutional neural networks (CNN). This paper provides a …

A small-sized object detection oriented multi-scale feature fusion approach with application to defect detection

N Zeng, P Wu, Z Wang, H Li, W Liu… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
Object detection is a well-known task in the field of computer vision, especially the small
target detection problem that has aroused great academic attention. In order to improve the …

TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios

X Zhu, S Lyu, X Wang, Q Zhao - Proceedings of the IEEE …, 2021‏ - openaccess.thecvf.com
Object detection on drone-captured scenarios is a recent popular task. As drones always
navigate in different altitudes, the object scale varies violently, which burdens the …

Yolo-facev2: A scale and occlusion aware face detector

Z Yu, H Huang, W Chen, Y Su, Y Liu, X Wang - Pattern Recognition, 2024‏ - Elsevier
In recent years, face detection algorithms based on deep learning have made great
progress. Nevertheless, the effective utilization of face detectors for small and occlusion …

Simple copy-paste is a strong data augmentation method for instance segmentation

G Ghiasi, Y Cui, A Srinivas, R Qian… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
Building instance segmentation models that are data-efficient and can handle rare object
categories is an important challenge in computer vision. Leveraging data augmentations is a …

A comparative analysis of object detection metrics with a companion open-source toolkit

R Padilla, WL Passos, TLB Dias, SL Netto… - Electronics, 2021‏ - mdpi.com
Recent outstanding results of supervised object detection in competitions and challenges
are often associated with specific metrics and datasets. The evaluation of such methods …

Rethinking counting and localization in crowds: A purely point-based framework

Q Song, C Wang, Z Jiang, Y Wang… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
Localizing individuals in crowds is more in accordance with the practical demands of
subsequent high-level crowd analysis tasks than simply counting. However, existing …

Varifocalnet: An iou-aware dense object detector

H Zhang, Y Wang, F Dayoub… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
Accurately ranking the vast number of candidate detections is crucial for dense object
detectors to achieve high performance. Prior work uses the classification score or a …

Align deep features for oriented object detection

J Han, J Ding, J Li, GS **a - IEEE transactions on geoscience …, 2021‏ - ieeexplore.ieee.org
The past decade has witnessed significant progress on detecting objects in aerial images
that are often distributed with large-scale variations and arbitrary orientations. However …