提出双向特征对齐机制，提升目标定位精度
BAFPN: Bi directional alignment of features to improve localization accuracy
- 在自底向上过程中用空间对齐模块全局校正特征错位
- 在自顶向下阶段通过语义对齐模块减少跨尺度融合伪影
- 在DOTAv1.5上提升AP75达1.68%，适合高精度检测任务
当前主流视觉模型多采用特征金字塔提取多尺度信息，其中特征金字塔网络（FPN）是最广泛使用的经典架构。然而，传统FPN及其变体（如AUGFPN、PAFPN）未能充分解决全局范围内的空间错位问题，导致高精度目标定位性能受限。本文提出一种新型双向对齐特征金字塔网络（BAFPN），在自底向上的信息传播阶段，通过空间特征对齐模块（SPAM）全局校正特征错位；在自顶向下的阶段，进一步利用细粒度语义对齐模块（SEAM）缓解跨尺度特征融合带来的混叠效应。在DOTAv1.5数据集上，BAFPN使基线模型的AP75、AP50和mAP分别提升1.68%、1.45%和1.34%。此外，BAFPN在多种先进检测器中均表现出显著性能提升。
原文摘要 · Abstract (English)
Current state-of-the-art vision models often utilize feature pyramids to extract multi-scale information, with the Feature Pyramid Network (FPN) being one of the most widely used classic architectures. However, traditional FPNs and their variants (e.g., AUGFPN, PAFPN) fail to fully address spatial misalignment on a global scale, leading to suboptimal performance in high-precision localization of objects. In this paper, we propose a novel Bidirectional Alignment Feature Pyramid Network (BAFPN), which aligns misaligned features globally through a Spatial Feature Alignment Module (SPAM) during the bottom-up information propagation phase. Subsequently, it further mitigates aliasing effects caused by cross-scale feature fusion via a fine-grained Semantic Alignment Module (SEAM) in the top-down phase. On the DOTAv1.5 dataset, BAFPN improves the baseline model's AP75, AP50, and mAP by 1.68%, 1.45%, and 1.34%, respectively. Additionally, BAFPN demonstrates significant performance gains when applied to various other advanced detectors.
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。