There is a tradeoff between generalization capability and computational overhead in multi-class learning. We propose a generative probabilistic multi-class classifier, considering both the generalization capability an...There is a tradeoff between generalization capability and computational overhead in multi-class learning. We propose a generative probabilistic multi-class classifier, considering both the generalization capability and the learning/prediction rate. We show that the classifier has a max-margin property. Thus, prediction on future unseen data can nearly achieve the same performance as in the training stage. In addition, local variables are eliminated, which greatly simplifies the optimization problem. By convex and probabilistic analysis, an efficient online learning algorithm is developed. The algorithm aggregates rather than averages dualities, which is different from the classical situations. Empirical results indicate that our method has a good generalization capability and coverage rate.展开更多
The performance of scene classification of satellite images strongly relies on the discriminative power of the low-level and mid-level feature representation. This paper presents a novel approach, named multi-level ma...The performance of scene classification of satellite images strongly relies on the discriminative power of the low-level and mid-level feature representation. This paper presents a novel approach, named multi-level max-margin analysis （M 3 DA） for semantic classification for high-resolution satellite images. In our M 3 DA model, the maximum entropy discrimination latent Dirichlet allocation （MedLDA） model is applied to learn the topic-level features first, and then based on a bag-of-words repre- sentation of low-level local image features, the large margin nearest neighbor （LMNN） classifier is used to optimize a multiple soft label composed of word-level features （generated by SVM classifier） and topic-level features. The categorization performances on 21-class land-use dataset have demonstrated that the proposed model in multi-level max-margin scheme can distinguish different categories of land-use scenes reasonably.展开更多
It is attractive to formulate problems in computer vision and related fields in term of probabilis- tic estimation where the probability models are defined over graphs, such as grammars. The graphical struc- tures, an...It is attractive to formulate problems in computer vision and related fields in term of probabilis- tic estimation where the probability models are defined over graphs, such as grammars. The graphical struc- tures, and the state variables defined over them, give a rich knowledge representation which can describe the complex structures of objects and images. The proba- bility distributions defined over the graphs capture the statistical variability of these structures. These proba- bility models can be learnt from training data with lim- ited amounts of supervision. But learning these models suffers from the difficulty of evaluating the normaliza- tion constant, or partition function, of the probability distributions which can be extremely computationally demanding. This paper shows that by placing bounds on the normalization constant we can obtain compu- rationally tractable approximations. Surprisingly, for certain choices of loss functions, we obtain many of the standard max-margin criteria used in support vector machines （SVMs） and hence we reduce the learning to standard machine learning methods. We show that many machine learning methods can be obtained in this way as approximations to probabilistic methods including multi-class max-margin, ordinal regression, max-margin Markov networks and parsers, multiple- instance learning, and latent SVM. We illustrate this work by computer vision applications including image labeling, object detection and localization, and motion estimation. We speculate that rained by using better bounds better results can be ob- and approximations.展开更多
基金Project supported by the National Natural Science Foundation of China （No. 61379069）, the Major Program of the National Social Science Foundation of China （No. 12＆ZD231）, and the National Key Technology R＆D Program of China （No. 2014BAK09B04）
文摘There is a tradeoff between generalization capability and computational overhead in multi-class learning. We propose a generative probabilistic multi-class classifier, considering both the generalization capability and the learning/prediction rate. We show that the classifier has a max-margin property. Thus, prediction on future unseen data can nearly achieve the same performance as in the training stage. In addition, local variables are eliminated, which greatly simplifies the optimization problem. By convex and probabilistic analysis, an efficient online learning algorithm is developed. The algorithm aggregates rather than averages dualities, which is different from the classical situations. Empirical results indicate that our method has a good generalization capability and coverage rate.
基金Supported by the Open Projects Program of National Laboratory of Pattern Recognition and the National Natural Science Foundation of China(91338113)
文摘The performance of scene classification of satellite images strongly relies on the discriminative power of the low-level and mid-level feature representation. This paper presents a novel approach, named multi-level max-margin analysis （M 3 DA） for semantic classification for high-resolution satellite images. In our M 3 DA model, the maximum entropy discrimination latent Dirichlet allocation （MedLDA） model is applied to learn the topic-level features first, and then based on a bag-of-words repre- sentation of low-level local image features, the large margin nearest neighbor （LMNN） classifier is used to optimize a multiple soft label composed of word-level features （generated by SVM classifier） and topic-level features. The categorization performances on 21-class land-use dataset have demonstrated that the proposed model in multi-level max-margin scheme can distinguish different categories of land-use scenes reasonably.
文摘It is attractive to formulate problems in computer vision and related fields in term of probabilis- tic estimation where the probability models are defined over graphs, such as grammars. The graphical struc- tures, and the state variables defined over them, give a rich knowledge representation which can describe the complex structures of objects and images. The proba- bility distributions defined over the graphs capture the statistical variability of these structures. These proba- bility models can be learnt from training data with lim- ited amounts of supervision. But learning these models suffers from the difficulty of evaluating the normaliza- tion constant, or partition function, of the probability distributions which can be extremely computationally demanding. This paper shows that by placing bounds on the normalization constant we can obtain compu- rationally tractable approximations. Surprisingly, for certain choices of loss functions, we obtain many of the standard max-margin criteria used in support vector machines （SVMs） and hence we reduce the learning to standard machine learning methods. We show that many machine learning methods can be obtained in this way as approximations to probabilistic methods including multi-class max-margin, ordinal regression, max-margin Markov networks and parsers, multiple- instance learning, and latent SVM. We illustrate this work by computer vision applications including image labeling, object detection and localization, and motion estimation. We speculate that rained by using better bounds better results can be ob- and approximations.
