In defense of local descriptor-based few-shot object detection
State-of-the-art image object detection computational models require an intensive parameter fine-tuning stage (using deep convolution network, etc). with tens or hundreds of training examples. In contrast, human intelligence can robustly learn a new concept from just a few instances (i.e., few-shot...
Main Authors: | Shichao Zhou, Haoyan Li, Zhuowei Wang, Zekai Zhang |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2024-02-01
|
Series: | Frontiers in Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2024.1349204/full |
Similar Items
-
Few-Shot Remote Sensing Image Scene Classification Based on Metric Learning and Local Descriptors
by: Zhengwu Yuan, et al.
Published: (2023-02-01) -
Few-Shot Text Classification with Global–Local Feature Information
by: Depei Wang, et al.
Published: (2022-06-01) -
MSFFAL: Few-Shot Object Detection via Multi-Scale Feature Fusion and Attentive Learning
by: Tianzhao Zhang, et al.
Published: (2023-03-01) -
Few-Shot Object Detection with Local Feature Enhancement and Feature Interrelation
by: Hefeng Lai, et al.
Published: (2023-09-01) -
Multi-Similarity Enhancement Network for Few-Shot Segmentation
by: Hao Chen, et al.
Published: (2023-01-01)