论文标题
通过语义对齐的匹配加速DETR收敛
Accelerating DETR Convergence via Semantic-Aligned Matching
论文作者
论文摘要
最近开发的检测变压器（DETR）通过消除一系列手工制作的组件来建立一个新的对象检测范例。但是，DETR的收敛速度极慢，这大大提高了训练成本。我们观察到，慢速收敛在很大程度上归因于将对象查询与不同特征嵌入空间中的目标特征匹配的并发症。本文介绍了SAM-DRE，这是一种与语义对齐的匹配DETR，它在不牺牲其准确性的情况下极大地加速了Detr的收敛性。 Sam-Detr从两个角度解决了融合问题。首先，它将对象查询与编码图像功能相同的嵌入空间，在该空间中可以通过对齐语义有效地完成匹配。其次，它以最有区别的特征来明确搜索与语义对齐的匹配的最大特征，从而进一步提高收敛性并提高检测准确性。就像插头一样，Sam-Detr可以很好地补充现有的收敛解决方案，但仅引入了轻微的计算开销。广泛的实验表明，所提出的SAM-DERTE可以达到优越的收敛性以及竞争性检测准确性。实施代码可在https://github.com/zhanggongjie/sam-detr上获得。
The recently developed DEtection TRansformer (DETR) establishes a new object detection paradigm by eliminating a series of hand-crafted components. However, DETR suffers from extremely slow convergence, which increases the training cost significantly. We observe that the slow convergence is largely attributed to the complication in matching object queries with target features in different feature embedding spaces. This paper presents SAM-DETR, a Semantic-Aligned-Matching DETR that greatly accelerates DETR's convergence without sacrificing its accuracy. SAM-DETR addresses the convergence issue from two perspectives. First, it projects object queries into the same embedding space as encoded image features, where the matching can be accomplished efficiently with aligned semantics. Second, it explicitly searches salient points with the most discriminative features for semantic-aligned matching, which further speeds up the convergence and boosts detection accuracy as well. Being like a plug and play, SAM-DETR complements existing convergence solutions well yet only introduces slight computational overhead. Extensive experiments show that the proposed SAM-DETR achieves superior convergence as well as competitive detection accuracy. The implementation codes are available at https://github.com/ZhangGongjie/SAM-DETR.
