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...
Hlavní autoři: | Jian Yao, Tianyun Shi, Xiaoping Che, Jie Yao, Liuyi Wu |
---|---|
Médium: | Článek |
Jazyk: | English |
Vydáno: |
IEEE
2023-01-01
|
Edice: | IEEE Access |
Témata: | |
On-line přístup: | https://ieeexplore.ieee.org/document/10227279/ |
Podobné jednotky
-
FSOD4RSI: Few-Shot Object Detection for Remote Sensing Images via Features Aggregation and Scale Attention
Autor: Honghao Gao, a další
Vydáno: (2024-01-01) -
Few-shot object detection based on positive-sample improvement
Autor: Yan Ouyang, a další
Vydáno: (2023-10-01) -
Multi-Similarity Enhancement Network for Few-Shot Segmentation
Autor: Hao Chen, a další
Vydáno: (2023-01-01) -
Few-Shot Object Detection in Remote Sensing Image Interpretation: Opportunities and Challenges
Autor: Sixu Liu, a další
Vydáno: (2022-09-01) -
Improving Augmentation Efficiency for Few-Shot Learning
Autor: Wonhee Cho, a další
Vydáno: (2022-01-01)