.png){kind=icon}
返回
AdaZoom: Towards Scale-Aware Large Scene Object Detection
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2022.3178871.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Detection in large scenes is a challenging issue due to small objects and extreme scale variation. It is difficult for the deep-learning-based detector to extract features of small objects with only a few pixels. Most existing methods employ image pyramid and feature pyramid for multi-scale inference to alleviate this issue. However, they lack scale awareness to adapt to objects with different scales. In this paper, we propose a novel Adaptive Zoom (AdaZoom) network for scale-aware large scene object detection. There are three main contributions. First, an Adaptive Zoom network is proposed to actively focus and adaptively zoom the focused regions for high-performance object detection in large scenes. Second, to tackle the problem of missing annotations for focused regions, we train AdaZoom with the reward which measures the quality of generated regions, based on the paradigm of deep reinforcement learning. At last, we propose collaborative training to iteratively promote the joint performance of AdaZoom and the detector. To validate the effectiveness, we conduct extensive experiments on VisDrone2019, UAVDT and DOTA datasets. The experiments show AdaZoom brings consistent and significant improvement over different detection networks, achieving state-of-the-art performance on these datasets, especially outperforming the existing methods by AP of 4.64% on VisDrone2019.
Keyword:
Object detection
large scenes
adaptive zooming
scale-aware
deep reinforcement learning
期刊
IF:
9.7
论文数:
4.5K
被引数:
2.4W
机构
引用论文
Conductivity Enhancement in Thin Silicon-on-Insulator Layer Embedding Artificial Dislocation Network
PREAI
分享收藏
Advances in the development of built-in diagnostic system for filament wound composite structures
PREAI
分享收藏CD4 cell count and CD4/CD8 ratio increase during rituximab maintenance in Granulomatosis with polyangiitis patients.png)
PeerJ
OAAI
PeerJIF0
OAAI分享收藏分享收藏
查看更多内容