.png){kind=icon}
返回
Deep Unsupervised Active Learning via Matrix Sketching
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2021.3124317.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Most existing unsupervised active learning methods aim at minimizing the data reconstruction loss by using the linear models to choose representative samples for manually labeling in an unsupervised setting. Thus these methods often fail in modelling data with complex non-linear structure. To address this issue, we propose a new deep unsupervised Active Learning method for classification tasks, inspired by the idea of Matrix Sketching, called ALMS. Specifically, ALMS leverages a deep auto-encoder to embed data into a latent space, and then describes all the embedded data with a small size sketch to summarize the major characteristics of the data. In contrast to previous approaches that reconstruct the whole data matrix for selecting the representative samples, ALMS aims to select a representative subset of samples to well approximate the sketch, which can preserve the major information of data meanwhile significantly reducing the number of network parameters. This makes our algorithm alleviate the issue of model overfitting and readily cope with large datasets. Actually, the sketch provides a type of self-supervised signal to guide the learning of the model. Moreover, we propose to construct an auxiliary self-supervised task by classifying real/fake samples, in order to further improve the representation ability of the encoder. We thoroughly evaluate the performance of ALMS on both single-label and multi-label classification tasks, and the results demonstrate its superior performance against the state-of-the-art methods. The code can be found at https://github.com/lrq99/ALMS.
Keyword:
Image reconstruction
Image processing
Data models
Task analysis
Learning systems
Kernel
Manifolds
Unsupervised active learning
matrix sketching
self-supervised learning
data reconstruction
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
引用论文
分享收藏Performance of Selected Herbaceous Annual Ornamentals Grown at Decreasing Levels of Irrigation在灌溉水平降低的情况下生长的某些草本一年生观赏植物的性能.png)
HortScience
OAAI
HortScienceIF0
OAAI分享收藏
查看更多内容