Label Distribution Learning by Mining Local Label Correlations in Self-regulating Clusters Independent of Sample Distance

Many aerial images with similar appearances have different but correlated scene labels, which causes the label ambiguity. Label distribution learning (LDL) can express label ambiguity by giving each sample a label distribution. Thus, a sample contributes to the learning of its ground-truth label as well as correlated labels, which improve data utilization. LDL has gained success in many fields, such as age estimation, in which label ambiguity can be easily modeled on the basis of the prior knowledge about local sample similarity and global label correlations. However, LDL has never been applied to scene classification, because there is no knowledge about the local similarity and label correlations and thus it is hard to model label ambiguity. In this paper, we uncover the sample neighbors that cause label ambiguity by jointly capturing the local similarity and label correlations and propose neighbor-based LDL (N-LDL) for aerial scene classification. We define a subspace learning problem, which formulates the neighboring relations as a coefficient matrix that is regularized by a sparse constraint and label correlations. The sparse constraint provides a few nearest neighbors, which captures local similarity. The label correlations are predefined according to the confusion matrices on validation sets. During subspace learning, the neighboring relations are encouraged to agree with the label correlations, which ensures that the uncovered neighbors have correlated labels. Finally, the label propagation among the neighbors forms the label distributions, which leads to label smoothing in terms of label ambiguity. The label distributions are used to train convolutional neural networks (CNNs). Experiments on the aerial image dataset (AID) and NWPU_RESISC45 (NR) datasets demonstrate that using the label distributions clearly improves the classification performance by assisting feature learning and mitigating over-fitting problems, and our method achieves state-of-the-art performance.

Download Full-text

Label Distribution Learning with Label Correlations via Low-Rank Approximation

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/461 ◽

2019 ◽

Cited By ~ 1

Author(s):

Tingting Ren ◽

Xiuyi Jia ◽

Weiwei Li ◽

Shu Zhao

Keyword(s):

Correlation Matrix ◽

Learning Algorithm ◽

Low Rank ◽

Low Rank Approximation ◽

Real World Data ◽

Label Correlations ◽

Rank Approximation ◽

Label Distribution Learning ◽

Label Distribution ◽

Label Correlation

Label distribution learning (LDL) can be viewed as the generalization of multi-label learning. This novel paradigm focuses on the relative importance of different labels to a particular instance. Most previous LDL methods either ignore the correlation among labels, or only exploit the label correlations in a global way. In this paper, we utilize both the global and local relevance among labels to provide more information for training model and propose a novel label distribution learning algorithm. In particular, a label correlation matrix based on low-rank approximation is applied to capture the global label correlations. In addition, the label correlation among local samples are adopted to modify the label correlation matrix. The experimental results on real-world data sets show that the proposed algorithm outperforms state-of-the-art LDL methods.

Download Full-text

Label distribution learning with label-specific features

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/460 ◽

2019 ◽

Cited By ~ 1

Author(s):

Tingting Ren ◽

Xiuyi Jia ◽

Weiwei Li ◽

Lei Chen ◽

Zechao Li

Keyword(s):

Feature Space ◽

Data Representation ◽

Data Sets ◽

Real World Data ◽

Feature Selection Problem ◽

Label Correlations ◽

The Common ◽

Label Distribution Learning ◽

Class Labels ◽

Label Distribution

Label distribution learning (LDL) is a novel machine learning paradigm to deal with label ambiguity issues by placing more emphasis on how relevant each label is to a particular instance. Many LDL algorithms have been proposed and most of them concentrate on the learning models, while few of them focus on the feature selection problem. All existing LDL models are built on a simple feature space in which all features are shared by all the class labels. However, this kind of traditional data representation strategy tends to select features that are distinguishable for all labels, but ignores label-specific features that are pertinent and discriminative for each class label. In this paper, we propose a novel LDL algorithm by leveraging label-specific features. The common features for all labels and specific features for each label are simultaneously learned to enhance the LDL model. Moreover, we also exploit the label correlations in the proposed LDL model. The experimental results on several real-world data sets validate the effectiveness of our method.

Download Full-text