| 摘要: |
| 目的 针对半监督目标检测导致数据特征表示不充分,数据样本类不均衡等问题,提出一种基于特征对齐和
特征融合的半监督目标检测方法。 方法 在常见的半监督目标检测框架中,伪标签是完全根据分类分数生成的,然
而,高置信度预测并不总是保证准确的 bbox 定位。 为了解决定位不准确问题和特征表示不充分问题,受 Consistent
Teacher 中的 FAM-3D 算法启发,考虑分类和定位的最优特征可能在不同尺度上,引入 T-head 特征对齐头算法,在
Unbiased Teacher V2 中成功地将分类和定位分支进行对齐,并且引入 ASFF,通过空间过滤冲突信息的方法来抑制
不一致性,从而提高了特征的尺度不变性,实现特征在空间上的融合;通过学习不同特征图之间的联系来解决特征
金字塔内部的不一致性问题。 结果 根据实验结果,改进的算法在 COCO 数据集、VOC 数据集上都有一定的比例提
升。 结论 改进的算法可以有效减轻数据表示不充分和数据样本类不均衡问题,同时也提高了算法的精度。 |
| 关键词: 目标检测 半监督学习 特征对齐 特征金字塔 ASFF |
| DOI： |
| 分类号: |
| 基金项目: |
|
| Semi-supervised Object Detection Algorithm Based on Feature Alignment and Feature Fusion |
|
TANG Wenbing LI Fei
|
|
School of Computer Science and Engineering Anhui University of Science and Technology Anhui Huainan 232001
China
|
| Abstract: |
| Objective In response to issues such as insufficient data feature representation and imbalanced sample classes
in semi-supervised object detection a semi-supervised object detection method based on feature alignment and feature
fusion was proposed. Methods In common semi-supervised object detection frameworks pseudo-labels are generated
solely based on classification scores. However high-confidence predictions do not always fully guarantee accurate bbox
positioning. In order to solve problems of inaccurate positioning and insufficient feature representation inspired by the
FAM-3D algorithm in the Consistent Teacher considering that the optimal features for classification and positioning may
be at different scales the T-head feature alignment head algorithm was introduced and the classification and positioning
branches were successfully aligned in Unbiased Teacher V2. Additionally ASFF was introduced to suppress inconsistency
by spatially filtering conflict information thereby improving the scale invariance of features and achieving spatial fusion of
features. The internal inconsistencies within the feature pyramid were addressed by learning the connections between
different feature maps. Results According to experimental results the improved algorithm demonstrated certain
performance improvements on the COCO dataset and VOC dataset. Conclusion The proposed algorithm effectively
alleviates issues of insufficient data representation and imbalanced sample classes while also enhancing algorithm
accuracy. |
| Key words: object detection semi-supervised learning feature alignment feature pyramid ASFF |
