.png){kind=icon}
返回
An Active Transfer Learning framework for image classification based on Maximum Differentiation Classifier
.png){kind=icon}
PRE
AI
DOI：10.1016/j.imavis.2024.105401.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep learning has been extensively adopted across various domains, yielding satisfactory outcomes. However, it heavily relies on extensive labeled datasets, collecting data labels is expensive and time-consuming. We propose a novel framework called Active Transfer Learning (ATL) to address this issue. The ATL framework consists of Active Learning (AL) and Transfer Learning (TL). AL queries the unlabeled samples with high inconsistency by Maximum Differentiation Classifier (MDC). The MDC pulls the discrepancy between the labeled data and their augmentations to select and annotate the informative samples. Additionally, we also explore the potential of incorporating TL techniques. The TL comprises pre-training and fine-tuning. The former learns knowledge from the origin-augmentation domain to pre-train the model, while the latter leverages the acquired knowledge for the downstream tasks. The results indicate that the combination of TL and AL exhibits complementary effects, while the proposed ATL framework outperforms state-of-the-art methods in terms of accuracy, precision, recall, and F1-score.
Keyword:
Active learning
Transfer learning
Image classification
Maximum differentiation classifier
期刊
IF:
4.2
论文数:
4.1K
被引数:
6.7K
机构
引用论文
分享收藏分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用.png)
PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏
查看更多内容