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...
Autori principali: | Jian Yao, Tianyun Shi, Xiaoping Che, Jie Yao, Liuyi Wu |
---|---|
Natura: | Articolo |
Lingua: | English |
Pubblicazione: |
IEEE
2023-01-01
|
Serie: | IEEE Access |
Soggetti: | |
Accesso online: | https://ieeexplore.ieee.org/document/10227279/ |
Documenti analoghi
Documenti analoghi
-
FSOD4RSI: Few-Shot Object Detection for Remote Sensing Images via Features Aggregation and Scale Attention
di: Honghao Gao, et al.
Pubblicazione: (2024-01-01) -
Few-shot object detection based on positive-sample improvement
di: Yan Ouyang, et al.
Pubblicazione: (2023-10-01) -
Multi-Similarity Enhancement Network for Few-Shot Segmentation
di: Hao Chen, et al.
Pubblicazione: (2023-01-01) -
Few-Shot Object Detection in Remote Sensing Image Interpretation: Opportunities and Challenges
di: Sixu Liu, et al.
Pubblicazione: (2022-09-01) -
Improving Augmentation Efficiency for Few-Shot Learning
di: Wonhee Cho, et al.
Pubblicazione: (2022-01-01)