Category‐related attention domain adaptation for one‐stage cross‐domain object detection
Abstract Cross‐domain object detection aims to generalize the distribution of features extracted by an object detector from an annotated domain to an unknown and unlabelled domain. Although one‐stage cross‐domain object detectors have significant advantages in deployment than two‐stage ones, they su...
Main Authors: | Shengxian Guan, Shuai Dong, Yuefang Gao, Kun Zou |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2024-02-01
|
Series: | IET Image Processing |
Subjects: | |
Online Access: | https://doi.org/10.1049/ipr2.12953 |
Similar Items
-
Small Object Detection in Infrared Images: Learning from Imbalanced Cross-Domain Data via Domain Adaptation
by: Jaekyung Kim, et al.
Published: (2022-11-01) -
LIDA‐YOLO: An unsupervised low‐illumination object detection based on domain adaptation
by: Yun Xiao, et al.
Published: (2024-04-01) -
AMA-Det: Enhancing Shared Head of One-Stage Object Detection With Adaptation, Merging, and Alignment
by: Song Cheng, et al.
Published: (2023-01-01) -
Toward cross‐domain object detection in artwork images using improved YoloV5 and XGBoosting
by: Tasweer Ahmad, et al.
Published: (2023-06-01) -
Spatial Alignment for Unsupervised Domain Adaptive Single-Stage Object Detection
by: Hong Liang, et al.
Published: (2022-04-01)