Meta-SSD: Towards Fast Adaptation for Few-Shot Object Detection With Meta-Learning

Meta-SSD: Towards Fast Adaptation for Few-Shot Object Detection With Meta-Learning

The state-of-the-art object detection frameworks require the training on large-scale datasets, which is the crux of the present dilemma: overfitting or degrading performance with insufficient samples and time-consuming training process. On the basis of meta-learning, this paper proposes a generalize...

Full description

Bibliographic Details
Main Authors: Kun Fu, Tengfei Zhang, Yue Zhang, Menglong Yan, Zhonghan Chang, Zhengyuan Zhang, Xian Sun
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Meta-learning
few-shot
object detection
fast adaptation
Online Access:https://ieeexplore.ieee.org/document/8735792/

Internet

https://ieeexplore.ieee.org/document/8735792/

Similar Items