Task-Oriented Local Feature Rectification Network for Few-Shot Image Classification
Few-shot image classification aims to classify unlabeled samples when only a small number of labeled samples are available for each class. Recently, local feature-based few-shot learning methods have made significant progress. However, existing methods often treat all local descriptors equally, with...
Saved in:
| Main Authors: | Ping Li, Xiang Zhu |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/9/1519 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
An efficient non-parametric feature calibration method for few-shot plant disease classification
by: Jiqing Li, et al.
Published: (2025-05-01) -
Feature Transformation-Based Few-Shot Class-Incremental Learning
by: Xubo Zhang, et al.
Published: (2025-07-01) -
An Unbiased Feature Estimation Network for Few-Shot Fine-Grained Image Classification
by: Jiale Wang, et al.
Published: (2024-12-01) -
Learning Class-Aware Local Representations for Few-Shot Remote Sensing Scene Classification
by: Liu Wang, et al.
Published: (2025-01-01) -
AlgaeClass_Net: Optimizing Few-Shot Marine Microalgae Classification With Multi-Scale Feature Enhancement Network
by: Dan Liu, et al.
Published: (2025-01-01)