arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.09093cs.CV
收藏

基于语义对齐的融合Transformer的单次目标检测

Semantic-aligned Fusion Transformer for One-shot Object Detection

Carnegie Mellon University(卡内基梅隆大学);Microsoft Research Asia(微软亚洲研究院)

Yizhou Zhao, Xun Guo, Yan Lu

摘要:

单次目标检测的目的是仅根据一个给定实例来检测新的目标。在数据极度稀缺的情况下,目前的方法探索各种特征融合以获得可直接转移的元知识。然而,他们的表现往往不能令人满意。在本文中,我们把这归因于不适当的相关方法,不一致的查询支持语义忽略空间结构和规模的变化。经过分析,我们利用注意力机制,并提出了一个简单而有效的架构命名为语义对齐的融合Transformer(SaFT)来解决这些问题。具体来说,我们配备了一个垂直融合模块(VFM)的跨尺度语义增强和水平融合模块(HFM)的跨样本特征融合的SaFT。总之,它们将每个特征点的视野从支持扩展到查询的整个增强特征金字塔,促进语义对齐的关联。在多个基准上的大量实验证明了我们框架的优越性。在不对新类进行微调的情况下,它为单阶段基线带来了显着的性能提升,将最先进的结果提升到更高的水平。

英文摘要:

One-shot object detection aims at detecting novel objects according to merely one given instance. With extreme data scarcity, current approaches explore various feature fusions to obtain directly transferable meta-knowledge. Yet, their performances are often unsatisfactory. In this paper, we attribute this to inappropriate correlation methods that misalign query-support semantics by overlooking spatial structures and scale variances. Upon analysis, we leverage the attention mechanism and propose a simple but effective architecture named Semantic-aligned Fusion Transformer (SaFT) to resolve these issues. Specifically, we equip SaFT with a vertical fusion module (VFM) for cross-scale semantic enhancement and a horizontal fusion module (HFM) for cross-sample feature fusion. Together, they broaden the vision for each feature point from the support to a whole augmented feature pyramid from the query, facilitating semantic-aligned associations. Extensive experiments on multiple benchmarks demonstrate the superiority of our framework. Without fine-tuning on novel classes, it brings significant performance gains to one-stage baselines, lifting state-of-the-art results to a higher level.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑