Cargando…
Corner-Point and Foreground-Area IoU Loss: Better Localization of Small Objects in Bounding Box Regression
Bounding box regression is a crucial step in object detection, directly affecting the localization performance of the detected objects. Especially in small object detection, an excellent bounding box regression loss can significantly alleviate the problem of missing small objects. However, there are...
Autores principales: | Cai, Delong, Zhang, Zhaoyun, Zhang, Zhi |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10223589/ https://www.ncbi.nlm.nih.gov/pubmed/37430876 http://dx.doi.org/10.3390/s23104961 |
Ejemplares similares
-
IoU Regression with H+L-Sampling for Accurate Detection Confidence
por: Wang, Dong, et al.
Publicado: (2021) -
Influence of Insufficient Dataset Augmentation on IoU and Detection Threshold in CNN Training for Object Detection on Aerial Images
por: Bożko, Arkadiusz, et al.
Publicado: (2022) -
Object Detection for UAV Aerial Scenarios Based on Vectorized IOU
por: Lu, Shun, et al.
Publicado: (2023) -
Alpha-SGANet: A multi-attention-scale feature pyramid network combined with lightweight network based on Alpha-IoU loss
por: Li, Hong, et al.
Publicado: (2022) -
Adaptive IoU Thresholding for Improving Small Object Detection: A Proof-of-Concept Study of Hand Erosions Classification of Patients with Rheumatic Arthritis on X-ray Images
por: Radke, Karl Ludger, et al.
Publicado: (2022)