arXiv subjects

Chun Yuan

Publications and source records attributed to Chun Yuan.

178 records · Page 10Linked to original sources

arXiv2020

StegColNet: Steganalysis based on an ensemble colorspace approach

Image steganography refers to the process of hiding information inside images. Steganalysis is the process of detecting a steganographic image. We introduce a steganalysis approach that uses an ensemble color space model to obtain a weighted concatenated feature activation map. The concatenated map helps to obtain certain features explicit to each color space. We use a levy-flight grey wolf optimization strategy to reduce the number of features selected in the map. We then use these features to classify the image into one of two classes: whether the given image has secret information stored or not. Extensive experiments have been done on a large scale dataset extracted from the Bossbase dataset. Also, we show that the model can be transferred to different datasets and perform extensive experiments on a mixture of datasets. Our results show that the proposed approach outperforms the recent state of the art deep learning steganalytical approaches by 2.32 percent on average for 0.2 bits per channel (bpc) and 1.87 percent on average for 0.4 bpc.

eess.IV↗

arXiv2020

A Simple Yet Effective Method for Video Temporal Grounding with Cross-Modality Attention

The task of language-guided video temporal grounding is to localize the particular video clip corresponding to a query sentence in an untrimmed video. Though progress has been made continuously in this field, some issues still need to be resolved. First, most of the existing methods rely on the combination of multiple complicated modules to solve the task. Second, due to the semantic gaps between the two different modalities, aligning the information at different granularities (local and global) between the video and the language is significant, which is less addressed. Last, previous works do not consider the inevitable annotation bias due to the ambiguities of action boundaries. To address these limitations, we propose a simple two-branch Cross-Modality Attention (CMA) module with intuitive structure design, which alternatively modulates two modalities for better matching the information both locally and globally. In addition, we introduce a new task-specific regression loss function, which improves the temporal grounding accuracy by alleviating the impact of annotation bias. We conduct extensive experiments to validate our method, and the results show that just with this simple model, it can outperform the state of the arts on both Charades-STA and ActivityNet Captions datasets.

cs.CV↗

arXiv2020

HOSE-Net: Higher Order Structure Embedded Network for Scene Graph Generation

Scene graph generation aims to produce structured representations for images, which requires to understand the relations between objects. Due to the continuous nature of deep neural networks, the prediction of scene graphs is divided into object detection and relation classification. However, the independent relation classes cannot separate the visual features well. Although some methods organize the visual features into graph structures and use message passing to learn contextual information, they still suffer from drastic intra-class variations and unbalanced data distributions. One important factor is that they learn an unstructured output space that ignores the inherent structures of scene graphs. Accordingly, in this paper, we propose a Higher Order Structure Embedded Network (HOSE-Net) to mitigate this issue. First, we propose a novel structure-aware embedding-to-classifier(SEC) module to incorporate both local and global structural information of relationships into the output space. Specifically, a set of context embeddings are learned via local graph based message passing and then mapped to a global structure based classification space. Second, since learning too many context-specific classification subspaces can suffer from data sparsity issues, we propose a hierarchical semantic aggregation(HSA) module to reduces the number of subspaces by introducing higher order structural information. HSA is also a fast and flexible tool to automatically search a semantic object hierarchy based on relational knowledge graphs. Extensive experiments show that the proposed HOSE-Net achieves the state-of-the-art performance on two popular benchmarks of Visual Genome and VRD.

cs.CV↗

arXiv2020

Automated Intracranial Artery Labeling using a Graph Neural Network and Hierarchical Refinement

Automatically labeling intracranial arteries (ICA) with their anatomical names is beneficial for feature extraction and detailed analysis of intracranial vascular structures. There are significant variations in the ICA due to natural and pathological causes, making it challenging for automated labeling. However, the existing public dataset for evaluation of anatomical labeling is limited. We construct a comprehensive dataset with 729 Magnetic Resonance Angiography scans and propose a Graph Neural Network (GNN) method to label arteries by classifying types of nodes and edges in an attributed relational graph. In addition, a hierarchical refinement framework is developed for further improving the GNN outputs to incorporate structural and relational knowledge about the ICA. Our method achieved a node labeling accuracy of 97.5%, and 63.8% of scans were correctly labeled for all Circle of Willis nodes, on a testing set of 105 scans with both healthy and diseased subjects. This is a significant improvement over available state-of-the-art methods. Automatic artery labeling is promising to minimize manual effort in characterizing the complicated ICA networks and provides valuable information for the identification of geometric risk factors of vascular disease. Our code and dataset are available at https://github.com/clatfd/GNN-ARTLABEL.

cs.CV↗

arXiv2020

Using an ensemble color space model to tackle adversarial examples

Minute pixel changes in an image drastically change the prediction that the deep learning model makes. One of the most significant problems that could arise due to this, for instance, is autonomous driving. Many methods have been proposed to combat this with varying amounts of success. We propose a 3 step method for defending such attacks. First, we denoise the image using statistical methods. Second, we show that adopting multiple color spaces in the same model can help us to fight these adversarial attacks further as each color space detects certain features explicit to itself. Finally, the feature maps generated are enlarged and sent back as an input to obtain even smaller features. We show that the proposed model does not need to be trained to defend an particular type of attack and is inherently more robust to black-box, white-box, and grey-box adversarial attack techniques. In particular, the model is 56.12 percent more robust than compared models in case of white box attacks when the models are not subject to adversarial example training.

cs.CV↗

arXiv2019

Automated Artery Localization and Vessel Wall Segmentation of Magnetic Resonance Vessel Wall Images using Tracklet Refinement and Polar Conversion

Quantitative analysis of vessel wall structures by automated vessel wall segmentation provides useful imaging biomarkers in evaluating atherosclerotic lesions and plaque progression time-efficiently. To quantify vessel wall features, drawing lumen and outer wall contours of the artery of interest is required. To alleviate manual labor in contour drawing, some computer-assisted tools exist, but manual preprocessing steps, such as region of interest identification and boundary initialization are needed. In addition, the prior knowledge of the ring shape of vessel wall is not taken into consideration in designing the segmentation method. In this work, trained on manual vessel wall contours, a fully automated artery localization and vessel wall segmentation system is proposed. A tracklet refinement algorithm is used to robustly identify the centerlines of arteries of interest from a neural network localization architecture. Image patches are extracted from the centerlines and segmented in a polar coordinate system to use 3D information and to overcome problems such as contour discontinuity and interference from neighboring vessels. From a carotid artery dataset with 116 subjects (3406 slices) and a popliteal artery dataset with 5 subjects (289 slices), the proposed system is shown to robustly identify the artery of interest and segment the vessel wall. The proposed system demonstrates better performance on the carotid dataset with a Dice similarity coefficient of 0.824, compared with traditional vessel wall segmentation methods, Dice of 0.576, and traditional convolutional neural network approaches, Dice of 0.747. This vessel wall segmentation system will facilitate research on atherosclerosis and assist radiologists in image review.

eess.IV↗

arXiv2019

Multi-Frame Content Integration with a Spatio-Temporal Attention Mechanism for Person Video Motion Transfer

Existing person video generation methods either lack the flexibility in controlling both the appearance and motion, or fail to preserve detailed appearance and temporal consistency. In this paper, we tackle the problem of motion transfer for generating person videos, which provides controls on both the appearance and the motion. Specifically, we transfer the motion of one person in a target video to another person in a source video, while preserving the appearance of the source person. Besides only relying on one source frame as the existing state-of-the-art methods, our proposed method integrates information from multiple source frames based on a spatio-temporal attention mechanism to preserve rich appearance details. In addition to a spatial discriminator employed for encouraging the frame-level fidelity, a multi-range temporal discriminator is adopted to enforce the generated video to resemble temporal dynamics of a real video in various time ranges. A challenging real-world dataset, which contains about 500 dancing video clips with complex and unpredictable motions, is collected for the training and testing. Extensive experiments show that the proposed method can produce more photo-realistic and temporally consistent person videos than previous methods. As our method decomposes the syntheses of the foreground and background into two branches, a flexible background substitution application can also be achieved.

cs.CV↗

arXiv2019

Fast Registration for cross-source point clouds by using weak regional affinity and pixel-wise refinement

Many types of 3D acquisition sensors have emerged in recent years and point cloud has been widely used in many areas. Accurate and fast registration of cross-source 3D point clouds from different sensors is an emerged research problem in computer vision. This problem is extremely challenging because cross-source point clouds contain a mixture of various variances, such as density, partial overlap, large noise and outliers, viewpoint changing. In this paper, an algorithm is proposed to align cross-source point clouds with both high accuracy and high efficiency. There are two main contributions: firstly, two components, the weak region affinity and pixel-wise refinement, are proposed to maintain the global and local information of 3D point clouds. Then, these two components are integrated into an iterative tensor-based registration algorithm to solve the cross-source point cloud registration problem. We conduct experiments on synthetic cross-source benchmark dataset and real cross-source datasets. Comparison with six state-of-the-art methods, the proposed method obtains both higher efficiency and accuracy.

cs.CV↗

arXiv2019

ColorNet: Investigating the importance of color spaces for image classification

Image classification is a fundamental application in computer vision. Recently, deeper networks and highly connected networks have shown state of the art performance for image classification tasks. Most datasets these days consist of a finite number of color images. These color images are taken as input in the form of RGB images and classification is done without modifying them. We explore the importance of color spaces and show that color spaces (essentially transformations of original RGB images) can significantly affect classification accuracy. Further, we show that certain classes of images are better represented in particular color spaces and for a dataset with a highly varying number of classes such as CIFAR and Imagenet, using a model that considers multiple color spaces within the same model gives excellent levels of accuracy. Also, we show that such a model, where the input is preprocessed into multiple color spaces simultaneously, needs far fewer parameters to obtain high accuracy for classification. For example, our model with 1.75M parameters significantly outperforms DenseNet 100-12 that has 12M parameters and gives results comparable to Densenet-BC-190-40 that has 25.6M parameters for classification of four competitive image classification datasets namely: CIFAR-10, CIFAR-100, SVHN and Imagenet. Our model essentially takes an RGB image as input, simultaneously converts the image into 7 different color spaces and uses these as inputs to individual densenets. We use small and wide densenets to reduce computation overhead and number of hyperparameters required. We obtain significant improvement on current state of the art results on these datasets as well.

cs.CV↗

arXiv2018

FPGA-based Acceleration System for Visual Tracking

Visual tracking is one of the most important application areas of computer vision. At present, most algorithms are mainly implemented on PCs, and it is difficult to ensure real-time performance when applied in the real scenario. In order to improve the tracking speed and reduce the overall power consumption of visual tracking, this paper proposes a real-time visual tracking algorithm based on DSST(Discriminative Scale Space Tracking) approach. We implement a hardware system on Xilinx XC7K325T FPGA platform based on our proposed visual tracking algorithm. Our hardware system can run at more than 153 frames per second. In order to reduce the resource occupation, our system adopts the batch processing method in the feature extraction module. In the filter processing module, the FFT IP core is time-division multiplexed. Therefore, our hardware system utilizes LUTs and storage blocks of 33% and 40%, respectively. Test results show that the proposed visual tracking hardware system has excellent performance.

cs.CV↗

arXiv2018

Efficient Multi-level Correlating for Visual Tracking

Correlation filter (CF) based tracking algorithms have demonstrated favorable performance recently. Nevertheless, the top performance trackers always employ complicated optimization methods which constraint their real-time applications. How to accelerate the tracking speed while retaining the tracking accuracy is a significant issue. In this paper, we propose a multi-level CF-based tracking approach named MLCFT which further explores the potential capacity of CF with two-stage detection: primal detection and oriented re-detection. The cascaded detection scheme is simple but competent to prevent model drift and accelerate the speed. An effective fusion method based on relative entropy is introduced to combine the complementary features extracted from deep and shallow layers of convolutional neural networks (CNN). Moreover, a novel online model update strategy is utilized in our tracker, which enhances the tracking performance further. Experimental results demonstrate that our proposed approach outperforms the most state-of-the-art trackers while tracking at speed of exceeded 16 frames per second on challenging benchmarks.

cs.CV↗

arXiv2018

Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments

In the NIPS 2017 Learning to Run challenge, participants were tasked with building a controller for a musculoskeletal model to make it run as fast as possible through an obstacle course. Top participants were invited to describe their algorithms. In this work, we present eight solutions that used deep reinforcement learning approaches, based on algorithms such as Deep Deterministic Policy Gradient, Proximal Policy Optimization, and Trust Region Policy Optimization. Many solutions use similar relaxations and heuristics, such as reward shaping, frame skipping, discretization of the action space, symmetry, and policy blending. However, each of the eight teams implemented different modifications of the known algorithms.

cs.LG↗

arXiv2017

Y-net: 3D intracranial artery segmentation using a convolutional autoencoder

Automated segmentation of intracranial arteries on magnetic resonance angiography (MRA) allows for quantification of cerebrovascular features, which provides tools for understanding aging and pathophysiological adaptations of the cerebrovascular system. Using a convolutional autoencoder (CAE) for segmentation is promising as it takes advantage of the autoencoder structure in effective noise reduction and feature extraction by representing high dimensional information with low dimensional latent variables. In this report, an optimized CAE model (Y-net) was trained to learn a 3D segmentation model of intracranial arteries from 49 cases of MRA data. The trained model was shown to perform better than the three traditional segmentation methods in both binary classification and visual evaluation.

eess.IV↗

arXiv2016

A coarse-to-fine algorithm for registration in 3D street-view cross-source point clouds

With the development of numerous 3D sensing technologies, object registration on cross-source point cloud has aroused researchers' interests. When the point clouds are captured from different kinds of sensors, there are large and different kinds of variations. In this study, we address an even more challenging case in which the differently-source point clouds are acquired from a real street view. One is produced directly by the LiDAR system and the other is generated by using VSFM software on image sequence captured from RGB cameras. When it confronts to large scale point clouds, previous methods mostly focus on point-to-point level registration, and the methods have many limitations.The reason is that the least mean error strategy shows poor ability in registering large variable cross-source point clouds. In this paper, different from previous ICP-based methods, and from a statistic view, we propose a effective coarse-to-fine algorithm to detect and register a small scale SFM point cloud in a large scale Lidar point cloud. Seen from the experimental results, the model can successfully run on LiDAR and SFM point clouds, hence it can make a contribution to many applications, such as robotics and smart city development.

cs.CV↗

arXiv2016

Learning Boltzmann Machine with EM-like Method

We propose an expectation-maximization-like(EMlike) method to train Boltzmann machine with unconstrained connectivity. It adopts Monte Carlo approximation in the E-step, and replaces the intractable likelihood objective with efficiently computed objectives or directly approximates the gradient of likelihood objective in the M-step. The EM-like method is a modification of alternating minimization. We prove that EM-like method will be the exactly same with contrastive divergence in restricted Boltzmann machine if the M-step of this method adopts special approximation. We also propose a new measure to assess the performance of Boltzmann machine as generative models of data, and its computational complexity is O(Rmn). Finally, we demonstrate the performance of EM-like method using numerical experiments.

cs.LG↗

arXiv2016

A Systematic Approach for Cross-source Point Cloud Registration by Preserving Macro and Micro Structures

We propose a systematic approach for registering cross-source point clouds. The compelling need for cross-source point cloud registration is motivated by the rapid development of a variety of 3D sensing techniques, but many existing registration methods face critical challenges as a result of the large variations in cross-source point clouds. This paper therefore illustrates a novel registration method which successfully aligns two cross-source point clouds in the presence of significant missing data, large variations in point density, scale difference and so on. The robustness of the method is attributed to the extraction of macro and micro structures. Our work has three main contributions: (1) a systematic pipeline to deal with cross-source point cloud registration; (2) a graph construction method to maintain macro and micro structures; (3) a new graph matching method is proposed which considers the global geometric constraint to robustly register these variable graphs. Compared to most of the related methods, the experiments show that the proposed method successfully registers in cross-source datasets, while other methods have difficulty achieving satisfactory results. The proposed method also shows great ability in same-source datasets.

cs.CV↗