Multi-Scale Receptive Field Attention Free Transformer Feature Extractor
Journal
2023 IEEE International Conference on Visual Communications and Image Processing, VCIP 2023
ISBN
9798350359855
Date Issued
2023-01-01
Author(s)
Abstract
Image feature point extraction is critical in several computer vision tasks like object detection, image stitching, visual re-localization, 3D reconstruction, and simultaneous localization and mapping (SLAM). In recent years, learning-based feature extractor approaches have become increasingly prevalent in computer vision and can achieve even better matching performance. Nevertheless, how to label and describe the discriminative feature is problematic. In this paper, we proposed a weakly-supervised learning approach that integrates a transformer and U-net-like convolution networks to better consider global and local contexts. Moreover, we concatenate multiple-size dilation convolutions to achieve a wider receptive field. Experiments show that the proposed approach has a performance and is robust to viewpoint change and illumination variation.
Subjects
attention free transformer | dilation convolution | feature extractor | U-net | weakly supervised
Type
conference paper