.png){kind=icon}
返回
Libra-SOD: Balanced label assignment for small object detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2024.112353.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Small object detection (SOD) is one of the notoriously challenging tasks in the computer vision community. Due to instances occupying fairly small regions and having limited overlap with priors (anchors or points), strict label assignment based on pre-defined IoU thresholds usually results in a lack of sufficient training samples for small objects. Despite center sampling or IoU statistic-based label assignment strategies mitigate imbalanced label assignment results, they struggle to deliver consistent gains for small, medium and large objects simultaneously. In this paper, we propose a novel model with a balanced label assignment (BLA) strategy for SOD in complex scenes, called Libra-SOD. First, the BLA is proposed, which considers both classification confidence and localization quality in the assignment process, and assigns the same number of positive samples to each Ground Truth. Second, to cooperate with BLA closely, we introduce a task-aware head, which makes the assignment results more reliable by interweaving classification and regression tasks. Finally, the task-aware loss is designed to dynamically assign weight factors and labels during supervised predictions, allowing the framework to focus more on valuable samples. Extensive experiments are performed on four challenging datasets. In DIOR (object DetectIon in Optical Remote sensing image), Libra-SOD achieves a state-of-the-art performance of 73.7 mAP with ResNet-50 as the backbone. To the best of our knowledge, Libra-SOD is the first single-stage framework that performs over 30 AP on SODA-D (Small Object Detection dAtasets).
Keyword:
Object detection
Small object detection
Balanced label assignment
Single-stage framework
期刊
K
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Conductivity Enhancement in Thin Silicon-on-Insulator Layer Embedding Artificial Dislocation Network
PREAI
分享收藏Multicomponent Orbital-Optimized Perturbation Theory with Density Fitting: Anharmonic Zero-Point Energies in Protonated Water Clusters具有密度拟合的多组分轨道优化摄动理论: 质子化水团簇中的非谐零点能量
PREAI
分享收藏A full data augmentation pipeline for small object detection based on generative adversarial networks基于生成对抗网络的小目标检测全数据增强流水线.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
查看更多内容