---
title: "Local Representation is Not Enough: Soft Point-Wise Transformer for Descriptor and Detector of Local Features"
authors:
  - "Zihao Wang"
  - "Xueyi Li"
  - "Zhen Li"
doi: "10.24963/ijcai.2021/159"
url: "https://ijcai.org/proceedings/2021/159"
pdf: "https://ijcai.org/proceedings/2021/0159.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "1150-1156"
track: "Main Track"
keywords:
  - "Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation"
  - "Computer Vision: 2D and 3D Computer Vision"
---

# Local Representation is Not Enough: Soft Point-Wise Transformer for Descriptor and Detector of Local Features

Zihao Wang, Xueyi Li, Zhen Li

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 1150-1156. DOI: [10.24963/ijcai.2021/159](https://doi.org/10.24963/ijcai.2021/159)

## Abstract

Significant progress has been witnessed for the descriptor and detector of local features, but there still exist several challenging and intractable limitations, such as insufficient localization accuracy and non-discriminative description, especially in repetitive- or blank-texture regions, which haven't be well addressed. The coarse feature representation and limited receptive field are considered as the main issues for these limitations. To address these issues, we propose a novel Soft Point-Wise Transformer for Descriptor and Detector, simultaneously mining long-range intrinsic and cross-scale dependencies of local features. Furthermore, our model leverages the distinct transformers based on the soft point-wise attention, substantially decreasing the memory and computation complexity, especially for high-resolution feature maps. In addition, multi-level decoder is constructed to guarantee the high detection accuracy and discriminative description. Extensive experiments demonstrate that our model outperforms the existing state-of-the-art methods on the image matching and visual localization benchmarks.