Abundant datasets generated from various big science projects on diseases have presented great challenges and opportunities, which contributed to unfolding the complexity of diseases. The discovery of disease-associated molecular networks for each individual plays an important role in personalized therapy and precision treatment of cancer-based on the reference networks. However, there are no effective ways to distinguish the consistency of different reference networks. In this study, we developed a statistical method, i.e. a sample-specific differential network (SSDN), to construct and analyze such networks based on gene expression of a single sample against a reference dataset. We proved that the SSDN is structurally consistent even with different reference datasets if the reference dataset can follow certain conditions. The SSDN also can be used to identify patient-specific disease modules or network biomarkers as well as predict the potential driver genes of a tumor sample.

BACKGROUND: Along with the development of precision medicine, individual heterogeneity is attracting more and more attentions in clinical research and application. Although the biomolecular reaction seems to be some various when different individuals suffer a same disease (e.g. virus infection), the final pathogen outcomes of individuals always can be mainly described by two categories in clinics, i.e. symptomatic and asymptomatic. Thus, it is still a great challenge to characterize the individual specific intrinsic regulatory convergence during dynamic gene regulation and expression. Except for individual heterogeneity, the sampling time also increase the expression diversity, so that, the capture of similar steady biological state is a key to characterize individual dynamic biological processes. RESULTS: Assuming the similar biological functions (e.g. pathways) should be suitable to detect consistent functions rather than chaotic genes, we design and implement a new computational framework (ABP: Attractor analysis of Boolean network of Pathway). ABP aims to identify the dynamic phenotype associated pathways in a state-transition manner, using the network attractor to model and quantify the steady pathway states characterizing the final steady biological sate of individuals (e.g. normal or disease). By analyzing multiple temporal gene expression datasets of virus infections, ABP has shown its effectiveness on identifying key pathways associated with phenotype change; inferring the consensus functional cascade among key pathways; and grouping pathway activity states corresponding to disease states. CONCLUSIONS: Collectively, ABP can detect key pathways and infer their consensus functional cascade during dynamical process (e.g. virus infection), and can also categorize individuals with disease state well, which is helpful for disease classification and prediction.

Deep convolutional neural networks (CNNs) have been widely and successfully applied in many computer vision tasks, such as classification, detection, semantic segmentation, and so on. As for image retrieval, while off-the-shelf CNN features from models trained for classification task are demonstrated promising, it remains a challenge to learn specific features oriented for instance retrieval. Witnessing the great success of low-level SIFT feature in image retrieval and its complementary nature to the semantic-aware CNN feature, in this paper, we propose to embed the SIFT feature into the CNN feature with a Siamese structure in a learning-based paradigm. The learning objective consists of two kinds of loss, i.e., similarity loss and fidelity loss. The first loss embeds the image-level nearest neighborhood structure with the SIFT feature into CNN feature learning, while the second loss imposes that the CNN feature with the updated CNN model preserves the fidelity of that from the original CNN model solely trained for classification. After the learning, the generated CNN feature inherits the property of the SIFT feature, which is well oriented for image retrieval. We evaluate our approach on the public data sets, and comprehensive experiments demonstrate the effectiveness of the proposed method.

Image retrieval has achieved remarkable improvements with the rapid progress on visual representation and indexing techniques. Given a query image, search engines are expected to retrieve relevant results in which the top-ranked short list is of most value to users. However, it is challenging to measure the retrieval quality on-the-fly without direct user feedbacks. In this paper, we aim at evaluating the quality of retrieval results at the first glance (i.e., with the top-ranked images). For each retrieval result, we compute a correlation based feature matrix that comprises of contextual information from the retrieval list, and then feed it into a convolutional neural network regression model for retrieval quality evaluation. In this proposed framework, multiple visual features are integrated together for robust representations. We optimize the output of this simpleyet- effective evaluation method to be consistent with Discounted Cumulative Gain (DCG), the intuitive measure for the quality of the top-ranked results. We evaluate our method in terms of prediction accuracy and consistency with the ground truth, and demonstrate its practicability in applications such as rank list selection and database image abundance analyses.

Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance on many visual recognition tasks. However, the combination of convolution and pooling operations only shows invariance to small local location changes in meaningful objects in input. Sometimes, such networks are trained using data augmentation to encode this invariance into the parameters, which restricts the capacity of the model to learn the content of these objects. A more efficient use of the parameter budget is to encode rotation or translation invariance into the model architecture, which relieves the model from the need to learn them. To enable the model to focus on learning the content of objects other than their locations, we propose to conduct patch ranking of the feature maps before feeding them into the next layer. When patch ranking is combined with convolution and pooling operations, we obtain consistent representations despite the location of meaningful objects in input. We show that the patch ranking module improves the performance of the CNN on many benchmark tasks, including MNIST digit recognition, large-scale image recognition, and image retrieval.

This paper presents a novel large-scale dataset and comprehensive baselines for end-to-end pedestrian detection and person recognition in raw video frames. Our baselines address three issues: the performance of various combinations of detectors and recognizers, mechanisms for pedestrian detection to help improve overall re-identification (re-ID) accuracy and assessing the effectiveness of different detectors for re-ID. We make three distinct contributions. First, a new dataset, PRW, is introduced to evaluate Person Re-identification in the Wild, using videos acquired through six synchronized cameras. It contains 932 identities and 11,816 frames in which pedestrians are annotated with their bounding box positions and identities. Extensive benchmarking results are presented on this dataset. Second, we show that pedestrian detection aids re-ID through two simple yet effective improvements: a cascaded fine-tuning strategy that trains a detection model first and then the classification model, and a Confidence Weighted Similarity (CWS) metric that incorporates detection scores into similarity measurement. Third, we derive insights in evaluating detector performance for the particular scenario of accurate person re-ID.

Different kinds of features hold some distinct merits, making them complementary to each other. Inspired by this idea an index level multiple feature fusion scheme via similarity matrix pooling is proposed in this paper. We first compute the similarity matrix of each index, and then a novel scheme is used to pool on these similarity matrices for updating the original indices. Compared with the existing fusion schemes, the proposed scheme performs feature fusion at index level to save memory and reduce computational complexity. On the other hand, the proposed scheme treats different kinds of features adaptively based on its importance, thus improves retrieval accuracy. The performance of the proposed approach is evaluated using two public datasets, which significantly outperforms the baseline methods in retrieval accuracy with low memory consumption and computational complexity.

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with sufficient layers and parameters, hierarchical combinations of convolution (matrix multiplication and non-linear activation) and pooling operations should be able to learn a robust mapping from transformed input images to transform-invariant representations. In this paper, we propose randomly transforming (rotation, scale, and translation) feature maps of CNNs during the training stage. This prevents complex dependencies of specific rotation, scale, and translation levels of training images in CNN models. Rather, each convolutional kernel learns to detect a feature that is generally helpful for producing the transform-invariant answer given the combinatorially large variety of transform levels of its input feature maps. In this way, we do not require any extra training supervision or modification to the optimization process and training images. We show that random transformation provides significant improvements of CNNs on many benchmark tasks, including small-scale image recognition, large-scale image recognition, and image retrieval.

In content-based visual object retrieval, image representation is one of the fundamental issues in improving retrieval performance. Existing works adopt either local SIFT-like features or holistic features, and may suffer sensitivity to noise or poor discrimination power. In this article, we propose a compact representation for scalable object retrieval from few generic object regions. The regions are identified with a general object detector and are described with a fusion of learning-based features and aggregated SIFT features. Further, we compress feature representation in large-scale image retrieval scenarios. We evaluate the performance of the proposed method on two public ground-truth datasets, with promising results. Experimental results on a million-scale image database demonstrate superior retrieval accuracy with efficiency gain in both computation and memory usage.