.png){kind=icon}
返回
ESOD: Efficient Small Object Detection on High-Resolution Images
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2024.3501853.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Enlarging input images is a straightforward and effective approach to promote small object detection. However, simple image enlargement is significantly expensive on both computations and GPU memory. In fact, small objects are usually sparsely distributed and locally clustered. Therefore, massive feature extraction computations are wasted on the non-target background area of images. Recent works have tried to pick out target-containing regions using an extra network and perform conventional object detection, but the newly introduced computation limits their final performance. In this paper, we propose to reuse the detector's backbone to conduct feature-level object-seeking and patch-slicing, which can avoid redundant feature extraction and reduce the computation cost. Incorporating with a sparse detection head, we are able to detect small objects on high-resolution inputs (e.g., 1080P or larger) for superior performance. The resulting Efficient Small Object Detection (ESOD) approach is a generic framework, which can be applied to both CNN- and ViT-based detectors to save the computation and GPU memory costs. Extensive experiments demonstrate the efficacy and efficiency of our method. In particular, our method consistently surpasses the SOTA detectors by a large margin (e.g., 8% gains on AP) on the representative VisDrone, UAVDT, and TinyPerson datasets. Code will be made public soon.
Keyword:
Feature extraction
Object detection
Detectors
Costs
Head
Neck
Image resolution
Graphics processing units
Visualization
Feeds
Small object detection
high-resolution detection
filter-then-detect
sparse detection
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
暂无机构信息
引用论文
分享收藏Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍？
PREAI
分享收藏
Comparative study of layer by layer assembled multilayer films based on graphene oxide and reduced graphene oxide on flexible polyurethane foam: flame retardant and smoke suppression properties.png)
RSC Advances
RSC AdvancesIF0
PREAI
分享收藏
查看更多内容