Disentangled feature representation for few-shot image classification
Learning the generalizable feature representation is critical to few-shot image classification. While recent works exploited task-specific feature embedding using meta-tasks for few-shot learning, they are limited in many challenging tasks as being distracted by the excursive features such as the ba...
Saved in:
Main Authors: | Cheng, Hao, Wang, Yufei, Li, Haoliang, Kot, Alex Chichung, Wen, Bihan |
---|---|
Other Authors: | School of Electrical and Electronic Engineering |
Format: | Article |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/170577 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Deep self-supervised representation learning for free-hand sketch
by: Xu, Peng, et al.
Published: (2022) -
Unsupervised domain adaptation in the wild via disentangling representation learning
by: Li, Haoliang, et al.
Published: (2022) -
GMFAD: Towards generalized visual recognition via multilayer feature alignment and disentanglement
by: Li, Haoliang, et al.
Published: (2022) -
EMD-based entropy features for micro-doppler mini-UAV classification
by: Ma, Xinyue, et al.
Published: (2020) -
HELA-VFA: a hellinger distance-attention-based feature aggregation network for few-shot classification
by: Lee, Gao Yu, et al.
Published: (2024)