摘要 :
We propose a novel global-local variational energy to automatically extract objects of interest from images. Previous formulations only incorporate local region potentials, which are sensitive to incorrectly classified pixels duri...
展开
We propose a novel global-local variational energy to automatically extract objects of interest from images. Previous formulations only incorporate local region potentials, which are sensitive to incorrectly classified pixels during iteration. We introduce a global likelihood potential to achieve better estimation of the foreground and background models and, thus, better extraction results. Extensive experiments demonstrate its efficacy.
收起
摘要 :
In the human category of learning, learning is studied in a supervised, an unsupervised, or a semisupervised way. The rare human semisupervised category of learning studies all focus on early learning. However, the impact of the s...
展开
In the human category of learning, learning is studied in a supervised, an unsupervised, or a semisupervised way. The rare human semisupervised category of learning studies all focus on early learning. However, the impact of the semisupervised category learning late in learning, when automaticity develops, is unknown. Therefore, in Experiment 1, all participants were first trained on the information-integration category structure for 2 days until they reached an expert level. Afterwards, half of the participants learned in a supervised way and the other half in a semisupervised way over two successive days. Both groups received an equal number of feedback trials. Finally, all participants took part in a test day where they were asked to respond as quickly as possible. Participants were significantly faster on this test in the semisupervised group than in the supervised group. This difference was not found on day 2, implying that the no-feedback trials in the semisupervised condition facilitated automaticity. Experiment 2 was designed to test whether the higher number of trials in the semisupervised condition of Experiment 1 caused the faster response times. We therefore created an almost supervised condition where participants almost always received feedback (95%) and an almost unsupervised condition where participants almost never received feedback (5%). All conditions now contained an equal number of trials to the semisupervised condition of Experiment 1. The results show that receiving feedback almost always or almost never led to slower response times than the semisupervised condition of Experiment 1. This confirms the advantage of semisupervised learning late in learning.
收起
摘要 :
Deep learning methodologies have been employed in several different fields, with an outstanding success in image recognition applications, such as material quality control, medical imaging, autonomous driving, etc. Deep learning m...
展开
Deep learning methodologies have been employed in several different fields, with an outstanding success in image recognition applications, such as material quality control, medical imaging, autonomous driving, etc. Deep learning models rely on the abundance of labeled observations to train a prospective model. These models are composed of millions of parameters to estimate, increasing the need of more training observations. Frequently, it is expensive to gather labeled observations of data, making the usage of deep learning models not ideal, as the model might overfit data. In a semisupervised setting, unlabeled data are used to improve the levels of accuracy and generalization of a model with small labeled datasets. Nevertheless, in many situations different unlabeled data sources might be available. This raises the risk of a significant distribution mismatch between the labeled and unlabeled datasets. Such phenomena can cause a considerable performance hit to typical semisupervised deep learning (SSDL) frameworks, which often assume that both labeled and unlabeled datasets are drawn from similar distributions. Therefore, in this article we study the latest approaches for SSDL for image recognition. Emphasis is made in SSDL models designed to deal with a distribution mismatch between the labeled and unlabeled datasets. We address open challenges with the aim to encourage the community to tackle them, and overcome the high data demand of traditional deep learning pipelines under real-world usage settings.
收起
摘要 :
Semisupervised classification (SSC) learns, from cheap unlabeled data and labeled data, to predict the labels of test instances. In order to make use of the information from unlabeled data, there should be an assumed relationship ...
展开
Semisupervised classification (SSC) learns, from cheap unlabeled data and labeled data, to predict the labels of test instances. In order to make use of the information from unlabeled data, there should be an assumed relationship between the true class structure and the data distribution. One assumption is that data points clustered together are likely to have the same class label. In this paper, we propose a new algorithm, namely, cluster-based regularization (ClusterReg) for SSC, that takes the partition given by a clustering algorithm as a regularization term in the loss function of an SSC classifier. ClusterReg makes predictions according to the cluster structure together with limited labeled data. The experiments confirmed that ClusterReg has a good generalization ability for real-world problems. Its performance is excellent when data follows this cluster assumption. Even when these clusters have misleading overlaps, it still outperforms other state-of-the-art algorithms.
收起
摘要 :
In this paper, we propose a new framework for hyperspectral image classification, namely pseudolabel guided kernel learning (PLKL). The proposed framework is capable of fully utilizing unlabeled samples, making it very effective t...
展开
In this paper, we propose a new framework for hyperspectral image classification, namely pseudolabel guided kernel learning (PLKL). The proposed framework is capable of fully utilizing unlabeled samples, making it very effective to handle the task with extremely limited training samples. Specifically, with multiple initial kernels and labeled samples, we first employ support vector machine (SVM) classifiers to predict pseudolabels independently for each unlabeled sample, and consistency voting is applied to the resulting pseudolabels to select and add a few unlabeled samples to the training set. Then, we refine the kernels to improve their discriminability with the augmented training set and a typical kernel learning method. Such phases are repeated until stable. Furthermore, we enhance the PLKL in terms of both the computation and memory efficiencies by using a bagging-like strategy, improving its practicality for large scale datasets. In addition, the proposed framework is quite flexible and general. That is, other advanced kernel-based methods can be incorporated to continuously improve the performance. Experimental results show that the proposed frameworks achieve much higher classification accuracy, compared with state-of-the-art methods. Especially, the classification accuracy improves more than 5% with very few training samples.
收起
摘要 :
We propose a framework for improving classifier performance by effectively using auxiliary samples. The auxiliary samples are labeled not in terms of the target taxonomy according to which we wish to classify samples, but accordin...
展开
We propose a framework for improving classifier performance by effectively using auxiliary samples. The auxiliary samples are labeled not in terms of the target taxonomy according to which we wish to classify samples, but according to classification schemes or taxonomies that are different from the target taxonomy. Our method finds a classifier by minimizing a weighted error over the target and auxiliary samples. The weights are defined so that the weighted error approximates the expected error when samples are classified into the target taxonomy. Experiments using synthetic and text data show that our method significantly improves the classifier performance in most cases compared to conventional data augmentation methods.
收起
摘要 :
Normalized graph Laplacian has been widely used in many practical machine learning algorithms, e.g., spectral clustering and semisupervised learning. However, all of them use the Euclidean distance to construct the graph Laplacian...
展开
Normalized graph Laplacian has been widely used in many practical machine learning algorithms, e.g., spectral clustering and semisupervised learning. However, all of them use the Euclidean distance to construct the graph Laplacian, which does not necessarily reflect the inherent distribution of the data. In this brief, we propose a method to directly optimize the normalized graph Laplacian by using pairwise constraints. The learned graph is consistent with equivalence and nonequivalence pairwise relationships, and thus it can better represent similarity between samples. Meanwhile, our approach, unlike metric learning, automatically determines the scale factor during the optimization. The learned normalized Laplacian matrix can be directly applied in spectral clustering and semisupervised learning algorithms. Comprehensive experiments demonstrate the effectiveness of the proposed approach.
收起
摘要 :
Recent work suggests knowledge sources can be added into the topic modeling process to label topics and improve topic discovery. The knowledge sources typically consist of a collection of human-constructed articles, each describin...
展开
Recent work suggests knowledge sources can be added into the topic modeling process to label topics and improve topic discovery. The knowledge sources typically consist of a collection of human-constructed articles, each describing a topic (article-topic) for an entire domain. However, these semisupervised topic models assume a corpus to contain topics on only a subset of a domain. Therefore, during inference, the model must consider which article-topics were theoretically used to generate the corpus. Since the knowledge sources tend to be quite large, the many article-topics considered slow down the inference process. The increase in execution time is significant, with knowledge source input greater than 103 becoming unfeasible for use in topic modeling. To increase the applicability of semisupervised topic models, approaches are needed to speed up the overall execution time. This paper presents a way of ranking knowledge source topics to satisfy the above goal. Our approach utilizes a knowledge source ranking, based on the PageRank algorithm, to determine the importance of an article-topic. By applying our ranking technique we can eliminate low scoring article-topics before inference, speeding up the overall process. Remarkably, this ranking technique can also improve perplexity and interpretability. Results show our approach to outperform baseline methods and significantly aid semisupervised topic models. In our evaluation, knowledge source rankings yield a 44% increase in topic retrieval f-score, a 42.6% increase in inter-inference topic elimination, a 64% increase in perplexity, a 30% increase in token assignment accuracy, a 20% increase in topic composition interpretability, and a 5% increase in document assignment interpretability over baseline methods.
收起
摘要 :
Unsupervised models can provide supplementary soft constraints to help classify new "target" data because similar instances in the target set are more likely to share the same class label. Such models can also help detect possible...
展开
Unsupervised models can provide supplementary soft constraints to help classify new "target" data because similar instances in the target set are more likely to share the same class label. Such models can also help detect possible differences between training and target distributions, which is useful in applications where concept drift may take place, as in transfer learning settings. This article describes a general optimization framework that takes as input class membership estimates from existing classifiers learned on previously encountered "source" (or training) data, as well as a similarity matrix from a cluster ensemble operating solely on the target (or test) data to be classified, and yields a consensus labeling of the target data. More precisely, the application settings considered are nontransductive semisupervised and transfer learning scenarios where the training data are used only to build an ensemble of classifiers and are subsequently discarded before classifying the target data. The framework admits a wide range of loss functions and classification/clustering methods. It exploits properties of Bregman divergences in conjunction with Legendre duality to yield a principled and scalable approach. A variety of experiments show that the proposed framework can yield results substantially superior to those provided by naively applying classifiers learned on the original task to the target data. In addition, we show that the proposed approach, even not being conceptually transductive, can provide better results compared to some popular transductive learning techniques.
收起
摘要 :
Unsupervised learning is of growing interest because it unlocks the potential held in vast amounts of unlabeled data to learn useful representations for inference. Autoencoders, a form of generative model, may be trained by learni...
展开
Unsupervised learning is of growing interest because it unlocks the potential held in vast amounts of unlabeled data to learn useful representations for inference. Autoencoders, a form of generative model, may be trained by learning to reconstruct unlabeled input data from a latent representation space. More robust representations may be produced by an autoencoder if it learns to recover clean input samples from corrupted ones. Representations may be further improved by introducing regularization during training to shape the distribution of the encoded data in the latent space. We suggest denoising adversarial autoencoders (AAEs), which combine denoising and regularization, shaping the distribution of latent space using adversarial training. We introduce a novel analysis that shows how denoising may be incorporated into the training and sampling of AAEs. Experiments are performed to assess the contributions that denoising makes to the learning of representations for classification and sample synthesis. Our results suggest that autoencoders trained using a denoising criterion achieve higher classification performance and can synthesize samples that are more consistent with the input data than those trained without a corruption process.
收起
原文获取