Zhixi Feng

Bio: Zhixi Feng is an academic researcher from Xidian University. The author has contributed to research in topics: Computer science & Hyperspectral imaging. The author has an hindex of 10, co-authored 30 publications receiving 514 citations.

A Survey of Deep Learning-Based Object Detection

Abstract: Object detection is one of the most important and challenging branches of computer vision, which has been widely applied in people's life, such as monitoring security, autonomous driving and so on, with the purpose of locating instances of semantic objects of a certain class. With the rapid development of deep learning algorithms for detection tasks, the performance of object detectors has been greatly improved. In order to understand the main development status of object detection pipeline thoroughly and deeply, in this survey, we analyze the methods of existing typical detection models and describe the benchmark datasets at first. Afterwards and primarily, we provide a comprehensive overview of a variety of object detection methods in a systematic manner, covering the one-stage and two-stage detectors. Moreover, we list the traditional and new applications. Some representative branches of object detection are analyzed as well. Finally, we discuss the architecture of exploiting these object detection methods to build an effective and efficient system and point out a set of development trends to better follow the state-of-the-art algorithms and further research.

Multipath Residual Network for Spectral-Spatial Hyperspectral Image Classification

Abstract: Convolutional neural networks (CNNs) have recently shown outstanding capability for hyperspectral image (HSI) classification. In this work, a novel CNN model is proposed, which is wider than other existing deep learning-based HSI classification models. Based on the fact that very deep residual networks (ResNets) behave like ensembles of relatively shallow networks, our proposed network, called multipath ResNet (MPRN), employs multiple residual functions in the residual blocks to make the network wider, rather than deeper. The proposed network consists of shorter-medium paths for efficient gradient flow and replaces the stacking of multiple residual blocks in ResNet with fewer residual blocks but more parallel residual functions in each of it. Experimental results on three real hyperspectral data sets demonstrate the superiority of the proposed method over several state-of-the-art classification methods.

Discriminative Spectral–Spatial Margin-Based Semisupervised Dimensionality Reduction of Hyperspectral Data

Abstract: The past few years have witnessed prosperity of spectral-spatial processing of hyperspectral images. In this letter, in order to determine the optimal projection subspace of spectrums, we define discriminate spectral-spatial margins (DSSMs) to reveal the local information of hyperspectral pixels and explore the global structures of both labeled and unlabeled data via low-rank representation (LRR). Heterogeneous and homogeneous spectral-spatial neighbors of hyperspectral pixels are used to define DSSMs. By maximizing the DSSM of hyperspectral data and casting an LRR manifold regularizer on finding better projection, both the local and global information of hyperspectral data can be well explored to determine more discriminative features. Some experiments are taken on several real hyperspectral data sets, and the results exhibit its efficiency and superiority to the counterparts, when only a small number of labeled samples are available.

Semi-supervised classification via kernel low-rank representation graph

Abstract: Sparse Representation based Graphs (SRGs) have attracted increasing interests in very recent years. However, for lacking global constraints on solutions to sparse representation, SRGs cannot accurately reveal data structure when data are grossly corrupted. In this paper, in order to achieve robust classification of wide range of datasets when only a small number of labeled samples are available, we advance a new semi-supervised kernel low-rank representation graph (SKLRG), by combining low-rank representation (LRR) with graphs and kernel trick. A kernel projection is first learned to find high-dimensional space where data have possible low-rank structure. Then a low-rank representation of the projected data is calculated from which we can derive a SKLRG matrix to evaluate data affinity and classify corrupted patterns. The proposed SKLRG can naturally reveal the relationship among data in the projected space, and can capture the global structure of complex data and implements more robust subspace segmentation. Moreover, connected weights of SKLRG are refined by pairwise constrains where label information is explored to further improve the classification results. Some experiments are taken on some benchmark datasets and Synthetic Aperture Radar (SAR) images that are corrupted by speckle noise. The results show that the proposed SKLRG can achieve better performance than its counterparts when there are only a small number of labeled samples.

Review of deep learning: concepts, CNN architectures, challenges, applications, future directions

Abstract: In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in the field of ML, thus achieving outstanding results on several complex cognitive tasks, matching or even beating those provided by human performance. One of the benefits of DL is the ability to learn massive amounts of data. The DL field has grown fast in the last few years and it has been extensively used to successfully address a wide range of traditional applications. More importantly, DL has outperformed well-known ML techniques in many domains, e.g., cybersecurity, natural language processing, bioinformatics, robotics and control, and medical information processing, among many others. Despite it has been contributed several works reviewing the State-of-the-Art on DL, all of them only tackled one aspect of the DL, which leads to an overall lack of knowledge about it. Therefore, in this contribution, we propose using a more holistic approach in order to provide a more suitable starting point from which to develop a full understanding of DL. Specifically, this review attempts to provide a more comprehensive survey of the most important aspects of DL and including those enhancements recently added to the field. In particular, this paper outlines the importance of DL, presents the types of DL techniques and networks. It then presents convolutional neural networks (CNNs) which the most utilized DL network type and describes the development of CNNs architectures together with their main features, e.g., starting with the AlexNet network and closing with the High-Resolution network (HR.Net). Finally, we further present the challenges and suggested solutions to help researchers understand the existing research gaps. It is followed by a list of the major DL applications. Computational tools including FPGA, GPU, and CPU are summarized along with a description of their influence on DL. The paper ends with the evolution matrix, benchmark datasets, and summary and conclusion.

Change-Point Detection in Time-Series Data by Relative Density-Ratio Estimation (情報論的学習理論と機械学習)

Abstract: The objective of change-point detection is to discover abrupt property changes lying behind time-series data. In this paper, we present a novel statistical change-point detection algorithm based on non-parametric divergence estimation between time-series samples from two retrospective segments. Our method uses the relative Pearson divergence as a divergence measure, and it is accurately and efficiently estimated by a method of direct density-ratio estimation. Through experiments on artificial and real-world datasets including human-activity sensing, speech, and Twitter messages, we demonstrate the usefulness of the proposed method.

Feature Learning Using Spatial-Spectral Hypergraph Discriminant Analysis for Hyperspectral Image

Abstract: Hyperspectral image (HSI) contains a large number of spatial-spectral information, which will make the traditional classification methods face an enormous challenge to discriminate the types of land-cover. Feature learning is very effective to improve the classification performances. However, the current feature learning approaches are mostly based on a simple intrinsic structure. To represent the complex intrinsic spatial-spectral of HSI, a novel feature learning algorithm, termed spatial-spectral hypergraph discriminant analysis (SSHGDA), has been proposed on the basis of spatial-spectral information, discriminant information, and hypergraph learning. SSHGDA constructs a reconstruction between-class scatter matrix, a weighted within-class scatter matrix, an intraclass spatial-spectral hypergraph, and an interclass spatial-spectral hypergraph to represent the intrinsic properties of HSI. Then, in low-dimensional space, a feature learning model is designed to compact the intraclass information and separate the interclass information. With this model, an optimal projection matrix can be obtained to extract the spatial-spectral features of HSI. SSHGDA can effectively reveal the complex spatial-spectral structures of HSI and enhance the discriminating power of features for land-cover classification. Experimental results on the Indian Pines and PaviaU HSI data sets show that SSHGDA can achieve better classification accuracies in comparison with some state-of-the-art methods.