提升小物体检测性能，通过多线索选样本+类别感知特征增强
MAFE R-CNN: Selecting More Samples to Learn Category-aware Features for Small Object Detection
- 用IoU、置信度和真实框大小三线索选择多样正样本
- 在SODA数据集上实现8.7%的mAP提升，显著改善小物体检测
- 适合需要精准检测小目标的场景，如遥感与医学图像分析
复杂环境中对小物体的检测始终是目标检测领域的重大挑战。本文指出，其根源在于检测器难以有效学习小物体的判别性特征，且训练时高质量小物体样本的选择困难。为此，提出多线索分配与特征增强的R-CNN（MAFE R-CNN）。该方法包含两个核心模块：一是多线索样本选择（MCSS），利用交并比（IoU）距离、预测类别置信度和真实标注区域大小作为信息线索，实现多样化正样本选取，保障训练中物体尺寸分布均衡；二是类别感知特征增强机制（CFEM），引入简单有效的类别感知记忆模块，探索物体特征间关系，并通过类别感知特征与候选框特征的交互增强表示能力。在大规模小物体数据集SODA上的全面实验验证了该方法的有效性。代码将公开。
原文摘要 · Abstract (English)
Small object detection in intricate environments has consistently represented a major challenge in the field of object detection. In this paper, we identify that this difficulty stems from the detectors' inability to effectively learn discriminative features for objects of small size, compounded by the complexity of selecting high-quality small object samples during training, which motivates the proposal of the Multi-Clue Assignment and Feature Enhancement R-CNN.Specifically, MAFE R-CNN integrates two pivotal components.The first is the Multi-Clue Sample Selection (MCSS) strategy, in which the Intersection over Union (IoU) distance, predicted category confidence, and ground truth region sizes are leveraged as informative clues in the sample selection process. This methodology facilitates the selection of diverse positive samples and ensures a balanced distribution of object sizes during training, thereby promoting effective model learning.The second is the Category-aware Feature Enhancement Mechanism (CFEM), where we propose a simple yet effective category-aware memory module to explore the relationships among object features. Subsequently, we enhance the object feature representation by facilitating the interaction between category-aware features and candidate box features.Comprehensive experiments conducted on the large-scale small object dataset SODA validate the effectiveness of the proposed method. The code will be made publicly available.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。