GMFAD: Towards generalized visual recognition via multilayer feature alignment and disentanglement
The deep learning based approaches which have been repeatedly proven to bring benefits to visual recognition tasks usually make a strong assumption that the training and test data are drawn from similar feature spaces and distributions. However, such an assumption may not always hold in various prac...
Saved in:
Main Authors: | Li, Haoliang, Wang, Shiqi, Wan, Renjie, Kot, Alex Chichung |
---|---|
Other Authors: | School of Electrical and Electronic Engineering |
Format: | Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/161899 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Unsupervised domain adaptation in the wild via disentangling representation learning
by: Li, Haoliang, et al.
Published: (2022) -
Disentangled feature representation for few-shot image classification
by: Cheng, Hao, et al.
Published: (2023) -
Decoupling cross-quadrature correlations using passive operations
by: Assad, Syed Muhamad, et al.
Published: (2020) -
A penalized likelihood approach in covariance graphical model selection
by: LIN NAN
Published: (2011) -
Reflection scene separation from a single image
by: Wan, Renjie, et al.
Published: (2022)