[HTML][HTML] 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 …
image recognition and classification. CNNs have several uses, some of which are object …
Deep learning-based detection from the perspective of small or tiny objects: A survey
K Tong, Y Wu - Image and Vision Computing, 2022 - Elsevier
Detecting small or tiny objects is always a difficult and challenging issue in computer vision.
In this paper, we provide a latest and comprehensive survey of deep learning-based …
In this paper, we provide a latest and comprehensive survey of deep learning-based …
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 …
navigate in different altitudes, the object scale varies violently, which burdens the …
Embracing single stride 3d object detector with sparse transformer
In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to
input scene size is significantly smaller compared to 2D detection cases. Overlooking this …
input scene size is significantly smaller compared to 2D detection cases. Overlooking this …
Detecting everything in the open world: Towards universal object detection
In this paper, we formally address universal object detection, which aims to detect every
scene and predict every category. The dependence on human annotations, the limited …
scene and predict every category. The dependence on human annotations, the limited …
A normalized Gaussian Wasserstein distance for tiny object detection
Detecting tiny objects is a very challenging problem since a tiny object only contains a few
pixels in size. We demonstrate that state-of-the-art detectors do not produce satisfactory …
pixels in size. We demonstrate that state-of-the-art detectors do not produce satisfactory …
Slicing aided hyper inference and fine-tuning for small object detection
Detection of small objects and objects far away in the scene is a major challenge in
surveillance applications. Such objects are represented by small number of pixels in the …
surveillance applications. Such objects are represented by small number of pixels in the …
RFLA: Gaussian receptive field based label assignment for tiny object detection
Detecting tiny objects is one of the main obstacles hindering the development of object
detection. The performance of generic object detectors tends to drastically deteriorate on tiny …
detection. The performance of generic object detectors tends to drastically deteriorate on tiny …
RSOD: Real-time small object detection algorithm in UAV-based traffic monitoring
W Sun, L Dai, X Zhang, P Chang, X He - Applied Intelligence, 2022 - Springer
The prevailing applications of Unmanned Aerial Vehicles (UAVs) in transportation systems
promote the development of object detection methods to collect real-time traffic information …
promote the development of object detection methods to collect real-time traffic information …
QueryDet: Cascaded sparse query for accelerating high-resolution small object detection
While general object detection with deep learning has achieved great success in the past
few years, the performance and efficiency of detecting small objects are far from satisfactory …
few years, the performance and efficiency of detecting small objects are far from satisfactory …