Scale Information Enhancement for Few-Shot Object Detection on Remote Sensing Images
Recently, deep learning-based object detection techniques have arisen alongside time-consuming training and data collection challenges. Although few-shot learning techniques can boost models with few samples to lighten the training load, these approaches still need to be improved when applied to rem...
Saved in:
Published in | Remote sensing (Basel, Switzerland) Vol. 15; no. 22; p. 5372 |
---|---|
Main Authors | , , , , |
Format | Journal Article |
Language | English |
Published |
Basel
MDPI AG
01.11.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Recently, deep learning-based object detection techniques have arisen alongside time-consuming training and data collection challenges. Although few-shot learning techniques can boost models with few samples to lighten the training load, these approaches still need to be improved when applied to remote-sensing images. Objects in remote-sensing images are often small with an uncertain scale. An insufficient amount of samples would further aggravate this issue, leading to poor detection performance. This paper proposes a Gaussian-scale enhancement (GSE) strategy and a multi-branch patch-embedding attention aggregation (MPEAA) module for cross-scale few-shot object detection to address this issue. Our model can enrich the scale information of an object and learn better multi-scale features to improve the performance of few-shot object detectors on remote sensing images. |
---|---|
ISSN: | 2072-4292 2072-4292 |
DOI: | 10.3390/rs15225372 |