English

Semantic-aligned Fusion Transformer for One-shot Object Detection

Computer Vision and Pattern Recognition 2022-03-22 v2

Abstract

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.

Keywords

Cite

@article{arxiv.2203.09093,
  title  = {Semantic-aligned Fusion Transformer for One-shot Object Detection},
  author = {Yizhou Zhao and Xun Guo and Yan Lu},
  journal= {arXiv preprint arXiv:2203.09093},
  year   = {2022}
}

Comments

Accepted by CVPR2022

R2 v1 2026-06-24T10:16:39.254Z