Graph-based semi-supervised learning (GSSL) studies the problem where in addition to a set of data points with few available labels, there also exists a graph structure that describes the underlying relationship between data items. In practice, structure uncertainty often occurs in graphs when edges exist between data with different labels, which may further results in prediction uncertainty of labels. Considering that Gaussian process generalizes well with few labels and can naturally model uncertainty, in this paper, we propose an Uncertainty aware Graph Gaussian Process based approach (UaGGP) for GSSL. UaGGP exploits the prediction uncertainty and label smooth regularization to guide each other during learning. To further subdue the effect of irrelevant neighbors, UaGGP also aggregates the clean representation in the original space and the learned representation. Experiments on benchmarks demonstrate the effectiveness of the proposed approach.

Open-set classification is a common problem in many real world tasks, where data is collected for known classes, and some novel classes occur at the test stage. In this paper, we focus on a more challenging case where the data examples collected for known classes are all unlabeled. Due to the high cost of label annotation, it is rather important to train a model with least labeled data for both accurate classification on known classes and effective detection of novel classes. Firstly, we propose an active learning method by incorporating structured sparsity with diversity to select representative examples for annotation. Then a latent low-rank representation is employed to simultaneously perform classification and novel class detection. Also, the method along with a fast optimization solution is extended to a multi-stage scenario, where classes occur and disappear in batches at each stage. Experimental results on multiple datasets validate the superiority of the proposed method with regard to different performance measures.

Deep convolutional neural networks have achieved great success in various applications. However, training an effective DNN model for a specific task is rather challenging because it requires a prior knowledge or experience to design the network architecture, repeated trial-and-error process to tune the parameters, and a large set of labeled data to train the model. In this paper, we propose to overcome these challenges by actively adapting a pre-trained model to a new task with less labeled examples. Specifically, the pre-trained model is iteratively fine tuned based on the most useful examples. The examples are actively selected based on a novel criterion, which jointly estimates the potential contribution of an instance on optimizing the feature representation as well as improving the classification model for the target task. On one hand, the pre-trained model brings plentiful information from its original task, avoiding redesign of the network architecture or training from scratch; and on the other hand, the labeling cost can be significantly reduced by active label querying. Experiments on multiple datasets and different pre-trained models demonstrate that the proposed approach can achieve cost-effective training of DNNs.

In the field of medical imaging research, renal segmentation is an important task which is tedious and error-prone when performed manually. Deep learning methods have been successfully applied to feature learning in medical applications. In this paper, We focused on the high accuracy of the classification task because of its effect on the accuracy of a better segmentation, and a Renal Segmentation Algorithm Combined Low-level Features with Deep Coding Feature from medicine images is proposed. Firstly, we use the advantage of Stacked auto-encoder networks to automatically learn the high-level features that capture the structured information and semantic context in the image. Several low-level features are extracted, which can effectively capture contrast and spatial information in the renal regions, and incorporated to compensate with the learned high-level features at the output of the very last fully connected layer. The concatenated feature vector is further fed into a Least squares SVM detector with Morlwet kernel to obtain classification results. We trained the deep network on medicine data set and experimentally shows that our proposed method has high classification accuracy and can speed up the clinical task to segment the renal.