arrow
返回

Improving Object Detection Using Weakly-Annotated Auxiliary Multi-Label Segmentation

delete2021-01-01
delete0
delete
OA
AI
Z
Zhengyu Xia *
C
Chen Zhang
J
Joohee Kim
DOI:10.1109/ACCESS.2021.3132225delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
With the rapid development of deep learning techniques, the performance of object detection has increased significantly. Recently, several approaches on joint learning of object detection and semantic segmentation have been proposed to exploit the complementary benefits of the two highly correlated tasks. In this work, we propose a weakly-annotated auxiliary multi-label segmentation network that boosts object detection performance without additional computational cost at inference. The proposed auxiliary segmentation network is trained using weakly-annotated dataset and therefore does not require expensive pixel-level annotations for training. Different from the previous approaches, we use multi-label segmentation to jointly supervise auxiliary segmentation and object detection for better occlusion handling. The proposed method can be integrated with any one-stage object detector such as RetinaNet, YOLOv3, YOLOv4, or SSD. Our experimental results on the MS COCO dataset show that the proposed method can improve the performance of popular one-stage object detectors without slowing down the inference speed regardless of the sub-optimal training sample selection schemes.
Keyword:
Object detection
Task analysis
Feature extraction
Detectors
Semantics
Image segmentation
Training
Deep learning
multi-task learning
object detection
semantic segmentation

期刊

IEEE Access 封面图
IEEE Access
IF:
3.6
论文数:
9.8W
被引数:
29.4W

机构

I
Illinois Institute of Technology
学者数:
3.8K
论文数: 3.9K
被引数: 4.2K
引用论文

引用论文

Functionalization, Modification, and Transformation of Platinum Chini Clusters
err2018-07-06
err0
PREAI
errBeatrice Berti; Cristina Femoni; Maria Carmela Iapalucci; Silvia Ruggieri; Stefano Zacchini
err分享
err收藏
学者 查看更多内容