Reconciliation of statistical and spatial sparsity for robust visual classification
Recent image classification algorithms, by learning deep features from large-scale datasets, have achieved significantly better results comparing to the classic feature-based approaches. However, there are still various challenges of image classifications in practice, such as classifying noisy image...
Saved in:
Main Authors: | Cheng, Hao, Yap, Kim-Hui, Wen, Bihan |
---|---|
Other Authors: | School of Electrical and Electronic Engineering |
Format: | Article |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/172865 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Pairwise sparsity preserving embedding for unsupervised subspace learning and classification
by: Zhang, Z., et al.
Published: (2014) -
Fast sparsity-based orthogonal dictionary learning for image restoration
by: Bao, C., et al.
Published: (2014) -
Label-to-region with continuity-biased bi-layer sparsity Priors
by: Liu, X., et al.
Published: (2014) -
Robust image analysis with sparse representation on quantized visual features
by: Bao, B.-K., et al.
Published: (2014) -
Visual classification with multitask joint sparse representation
by: Yuan, X.-T., et al.
Published: (2014)