DA-FSOD: A Novel Data Augmentation Scheme for Few-Shot Object Detection
Deep learning techniques continue to be used in various applications in recent years. However, when it is difficult to obtain adequate training samples, the performance of the depth model will degrade. Although few-shot learning and data enhancement techniques can relieve this dilemma, the diversity...
Main Authors: | Jian Yao, Tianyun Shi, Xiaoping Che, Jie Yao, Liuyi Wu |
---|---|
Format: | Article |
Sprog: | English |
Udgivet: |
IEEE
2023-01-01
|
Serier: | IEEE Access |
Fag: | |
Online adgang: | https://ieeexplore.ieee.org/document/10227279/ |
Lignende værker
-
FSOD4RSI: Few-Shot Object Detection for Remote Sensing Images via Features Aggregation and Scale Attention
af: Honghao Gao, et al.
Udgivet: (2024-01-01) -
Few-shot object detection based on positive-sample improvement
af: Yan Ouyang, et al.
Udgivet: (2023-10-01) -
Multi-Similarity Enhancement Network for Few-Shot Segmentation
af: Hao Chen, et al.
Udgivet: (2023-01-01) -
Few-Shot Object Detection in Remote Sensing Image Interpretation: Opportunities and Challenges
af: Sixu Liu, et al.
Udgivet: (2022-09-01) -
Improving Augmentation Efficiency for Few-Shot Learning
af: Wonhee Cho, et al.
Udgivet: (2022-01-01)