Multi-Modal Curriculum Learning for Semi-Supervised Image Classification

Gong, Chen; Tao, Dacheng; Maybank, Stephen J.; Liu, Wei; Kang, Guoliang; Yang, Jie

doi:10.1109/tip.2016.2563981

Cited by 265 publications

(90 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, semi-supervised learning methods have been widely studied [27][28][29][30][31]. One classical semi-supervised learning method is co-training [29] which utilizes multi-view features to retrain the classifiers to obtain better performance.…”

Section: Introductionmentioning

confidence: 99%

Semi-supervised dictionary learning with label propagation for image classification

Chen

Yang

2017

Comp. Visual Media

View full text Add to dashboard Cite

Sparse coding and supervised dictionary learning have rapidly developed in recent years, and achieved impressive performance in image classification. However, there is usually a limited number of labeled training samples and a huge amount of unlabeled data in practical image classification, which degrades the discrimination of the learned dictionary. How to effectively utilize unlabeled training data and explore the information hidden in unlabeled data has drawn much attention of researchers. In this paper, we propose a novel discriminative semisupervised dictionary learning method using label propagation (SSD-LP). Specifically, we utilize a label propagation algorithm based on class-specific reconstruction errors to accurately estimate the identities of unlabeled training samples, and develop an algorithm for optimizing the discriminative dictionary and discriminative coding vectors simultaneously. Extensive experiments on face recognition, digit recognition, and texture classification demonstrate the effectiveness of the proposed method.

show abstract

Section: Introductionmentioning

confidence: 99%

Semi-supervised dictionary learning with label propagation for image classification

Chen

Yang

2017

Comp. Visual Media

View full text Add to dashboard Cite

show abstract

“…Generally, an important aspect of such works is that these features are often complementary, since they are from different measurements representing the same subject(s). On the other hand, it is evident that each individual modality alone cannot characterize the categories comprehensively, as each of them encodes different but interrelated properties of the data (Chaudhuri et al 2009; Xu et al 2013; Gong et al 2016; Luo et al 2013a; 2013b). Considering each modality (or type of features) as one view of the data, we propose to model the problem as a multi-view learning framework.…”

Section: Introductionmentioning

confidence: 99%

Multi-view feature selection and classification for Alzheimer’s Disease diagnosis

Zhang

Yang

Shen

et al. 2016

Multimed Tools Appl

View full text Add to dashboard Cite

In this paper, we propose a novel multi-view learning method for Alzheimer’s Disease (AD) diagnosis, using neuroimaging and genetics data. Generally, there are several major challenges associated with traditional classification methods on multi-source imaging and genetics data. First, the correlation between the extracted imaging features and class labels is generally complex, which often makes the traditional linear models ineffective. Second, medical data may be collected from different sources (i.e., multiple modalities of neuroimaging data, clinical scores or genetics measurements), therefore, how to effectively exploit the complementarity among multiple views is of great importance. In this paper, we propose a Multi-Layer Multi-View Classification (ML-MVC) approach, which regards the multi-view input as the first layer, and constructs a latent representation to explore the complex correlation between the features and class labels. This captures the high-order complementarity among different views, as we exploit the underlying information with a low-rank tensor regularization. Intrinsically, our formulation elegantly explores the nonlinear correlation together with complementarity among different views, and thus improves the accuracy of classification. Finally, the minimization problem is solved by the Alternating Direction Method of Multipliers (ADMM). Experimental results on Alzheimers Disease Neuroimaging Initiative (ADNI) data sets validate the effectiveness of our proposed method.

show abstract

“…Semi-supervised learning from data is one of the fundamental challenges in artificial intelligence, which considers the problem when only a subset of the observations has corresponding class labels [9]. This issue is of immense practical interest in a broad range of application scenarios, such as abnormal activity detection [39], neurological diagnosis [28], computer vision [10], and recommender Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored.…”

Section: Introductionmentioning

confidence: 99%

Adversarial Variational Embedding for Robust Semi-supervised Learning

Zhang

Yao

Yuan

2019

Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

Semi-supervised learning is sought for leveraging the unlabelled data when labelled data is difficult or expensive to acquire. Deep generative models (e.g., Variational Autoencoder (VAE)) and semisupervised Generative Adversarial Networks (GANs) have recently shown promising performance in semi-supervised classification for the excellent discriminative representing ability. However, the latent code learned by the traditional VAE is not exclusive (repeatable) for a specific input sample, which prevents it from excellent classification performance. In particular, the learned latent representation depends on a non-exclusive component which is stochastically sampled from the prior distribution. Moreover, the semi-supervised GAN models generate data from pre-defined distribution (e.g., Gaussian noises) which is independent of the input data distribution and may obstruct the convergence and is difficult to control the distribution of the generated data. To address the aforementioned issues, we propose a novel Adversarial Variational Embedding (AVAE) framework for robust and effective semi-supervised learning to leverage both the advantage of GAN as a high quality generative model and VAE as a posterior distribution learner. The proposed approach first produces an exclusive latent code by the model which we call VAE++, and meanwhile, provides a meaningful prior distribution for the generator of GAN. The proposed approach is evaluated over four different real-world applications and we show that our method outperforms the state-of-the-art models, which confirms that the combination of VAE++ and GAN can provide significant improvements in semisupervised classification.

show abstract

Multi-Modal Curriculum Learning for Semi-Supervised Image Classification

Cited by 265 publications

References 36 publications

Semi-supervised dictionary learning with label propagation for image classification

Semi-supervised dictionary learning with label propagation for image classification

Multi-view feature selection and classification for Alzheimer’s Disease diagnosis

Adversarial Variational Embedding for Robust Semi-supervised Learning

Contact Info

Product

Resources

About