.png){kind=icon}
返回
Generative Multi-Label Correlation Learning
.png){kind=icon}
PRE
AI
DOI：10.1145/3538708.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In real-world applications, a single instance could have more than one label. To solve this task, multi-label learning methods emerged in recent years. It is a more challenging problem for many reasons, such as complex label correlation, long-tail label distribution, and data shortage. In general, overcoming these challenges and bettering learning performance could be achieved by utilizing more training samples and including label correlations. However, these solutions are expensive and inflexible. Large-scale, well-labeled datasets are difficult to obtain, and building label correlation maps requires task-specific semantic information as prior knowledge. To address these limitations, we propose a general and compact Multi-Label Correlation Learning (MUCO) framework. MUCO explicitly and effectively learns the latent label correlations by updating a label correlation tensor, which provides highly accurate and interpretable prediction results. In addition, a multilabel generative strategy is deployed to handle the long-tail label distribution challenge. It borrows the visual clues from limited samples and synthesizes more diverse samples. All networks in our model are optimized simultaneously. Extensive experiments illustrate the effectiveness and efficiency of MUCO. Ablation studies further prove the effectiveness of all the modules.
Keyword:
Correlation learning
multi-label learning
image annotation
image retrieval
期刊
IF:
4.8
论文数:
1.3K
被引数:
4.4K
机构
引用论文
分享收藏
Non-Circadian Expression Masking Clock-Driven Weak Transcription Rhythms in U2OS Cells.png)
PLoS ONE
OAAI
PLoS ONEIF0
OAAI分享收藏分享收藏
查看更多内容