Image classification with limited data information
Image classification is a fundamental problem in image processing and computer vision. Recent algorithms have achieved significantly better results by learning deep features from large-scale datasets, such as ImageNet. However, in practice, challenges persist, especially with (I) low-quality image d...
Main Author: | Cheng, Hao |
---|---|
Other Authors: | Wen Bihan |
Format: | Thesis-Doctor of Philosophy |
Language: | English |
Published: |
Nanyang Technological University
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/174167 |
Similar Items
-
Proto-Adapter: Efficient Training-Free CLIP-Adapter for Few-Shot Image Classification
by: Naoki Kato, et al.
Published: (2024-06-01) -
From Sample Poverty to Rich Feature Learning: A New Metric Learning Method for Few-Shot Classification
by: Lei Zhang, et al.
Published: (2024-01-01) -
Revisiting the Transferability of Few-Shot Image Classification: A Frequency Spectrum Perspective
by: Min Zhang, et al.
Published: (2024-05-01) -
Adaptive prototype few-shot image classification method based on feature pyramid
by: Linshan Shen, et al.
Published: (2024-10-01) -
TMNIO:Triplet merged network with involution operators for improved few‐shot image classification
by: Qi Lulu, et al.
Published: (2024-05-01)