Label Enhancement for Label Distribution Learning via Prior Knowledge

Label distribution learning (LDL) is a novel machine learning paradigm that gives a description degree of each label to an instance. However, most of training datasets only contain simple logical labels rather than label distributions due to the difficulty of obtaining the label distributions directly. We propose to use the prior knowledge to recover the label distributions. The process of recovering the label distributions from the logical labels is called label enhancement. In this paper, we formulate the label enhancement as a dynamic decision process. Thus, the label distribution is adjusted by a series of actions conducted by a reinforcement learning agent according to sequential state representations. The target state is defined by the prior knowledge. Experimental results show that the proposed approach outperforms the state-of-the-art methods in both age estimation and image emotion recognition.

[1]  Jufeng Yang,et al.  Joint Image Emotion Classification and Distribution Learning via Deep Convolutional Neural Network , 2017, IJCAI.

[2]  Zhang Yi,et al.  Fuzzy SVM with a new fuzzy membership function , 2006, Neural Computing & Applications.

[3]  Zhi-Hua Zhou,et al.  Multi-Instance Multi-Label Learning with Application to Scene Classification , 2006, NIPS.

[4]  Xin Geng,et al.  Leveraging Implicit Relative Labeling-Importance Information for Effective Multi-label Learning , 2015, 2015 IEEE International Conference on Data Mining.

[5]  Tom Schaul,et al.  Dueling Network Architectures for Deep Reinforcement Learning , 2015, ICML.

[6]  Jianxin Wu,et al.  Age Estimation Using Expectation of Label Distribution Learning , 2018, IJCAI.

[7]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[8]  Ning Xu,et al.  Label Enhancement for Label Distribution Learning , 2018, IEEE Transactions on Knowledge and Data Engineering.

[9]  Yujie Liu,et al.  Weather-to-garment: Weather-oriented clothing recommendation , 2017, 2017 IEEE International Conference on Multimedia and Expo (ICME).

[10]  Xin Geng,et al.  Pre-release Prediction of Crowd Opinion on Movies by Label Distribution Learning , 2015, IJCAI.

[11]  Xin Geng,et al.  Soft video parsing by label distribution learning , 2018, Frontiers of Computer Science.

[12]  Sebastián Ventura,et al.  A Tutorial on Multilabel Learning , 2015, ACM Comput. Surv..

[13]  Jufeng Yang,et al.  Learning Visual Sentiment Distributions via Augmented Conditional Probability Neural Network , 2017, AAAI.

[14]  Kun Yi,et al.  Probabilistic End-To-End Noise Correction for Learning With Noisy Labels , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Xuan Zhang,et al.  Emotion Distribution Learning from Texts , 2016, EMNLP.

[16]  Xin Geng,et al.  Crowd counting in public video surveillance by label distribution learning , 2015, Neurocomputing.

[17]  Sam J. Maglio,et al.  Emotional category data on images from the international affective picture system , 2005, Behavior research methods.

[18]  R. Rosenfeld.  Nature , 2009, Otolaryngology--head and neck surgery : official journal of American Academy of Otolaryngology-Head and Neck Surgery.

[19]  Min-Ling Zhang,et al.  A Review on Multi-Label Learning Algorithms , 2014, IEEE Transactions on Knowledge and Data Engineering.

[20]  Yuxin Peng,et al.  StackDRL: Stacked Deep Reinforcement Learning for Fine-grained Visual Categorization , 2018, IJCAI.

[21]  Zhi-Hua Zhou,et al.  Facial Age Estimation by Learning from Label Distributions , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[23]  Jianxin Wu,et al.  Deep Label Distribution Learning With Label Ambiguity , 2016, IEEE Transactions on Image Processing.

[24]  Grigorios Tsoumakas,et al.  Multi-Label Classification: An Overview , 2007, Int. J. Data Warehous. Min..

[25]  Karl Ricanek,et al.  MORPH: a longitudinal image database of normal adult age-progression , 2006, 7th International Conference on Automatic Face and Gesture Recognition (FGR06).

[26]  Xin Geng,et al.  Multi-Label Manifold Learning , 2016, AAAI.

[27]  Thomas S. Huang,et al.  Human age estimation using bio-inspired features , 2009, CVPR.

[28]  Timothy F. Cootes,et al.  Toward Automatic Simulation of Aging Effects on Face Images , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[29]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[30]  Shuicheng Yan,et al.  Graph embedding: a general framework for dimensionality reduction , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[31]  Günther Palm,et al.  A Study of the Robustness of KNN Classifiers Trained Using Soft Labels , 2006, ANNPR.

[32]  Xin Geng,et al.  Soft Facial Landmark Detection by Label Distribution Learning , 2019, AAAI.