arXiv subjects

Jiawei Chen

Publications and source records attributed to Jiawei Chen.

At least 271 records · Page 15Linked to original sources

arXiv2020

Instance-aware Self-supervised Learning for Nuclei Segmentation

Due to the wide existence and large morphological variances of nuclei, accurate nuclei instance segmentation is still one of the most challenging tasks in computational pathology. The annotating of nuclei instances, requiring experienced pathologists to manually draw the contours, is extremely laborious and expensive, which often results in the deficiency of annotated data. The deep learning based segmentation approaches, which highly rely on the quantity of training data, are difficult to fully demonstrate their capacity in this area. In this paper, we propose a novel self-supervised learning framework to deeply exploit the capacity of widely-used convolutional neural networks (CNNs) on the nuclei instance segmentation task. The proposed approach involves two sub-tasks (i.e., scale-wise triplet learning and count ranking), which enable neural networks to implicitly leverage the prior-knowledge of nuclei size and quantity, and accordingly mine the instance-aware feature representations from the raw data. Experimental results on the publicly available MoNuSeg dataset show that the proposed self-supervised learning approach can remarkably boost the segmentation accuracy of nuclei instance---a new state-of-the-art average Aggregated Jaccard Index (AJI) of 70.63%, is achieved by our self-supervised ResUNet-101. To our best knowledge, this is the first work focusing on the self-supervised learning for instance segmentation.

cs.CV↗

arXiv2020

Self-Loop Uncertainty: A Novel Pseudo-Label for Semi-Supervised Medical Image Segmentation

Witnessing the success of deep learning neural networks in natural image processing, an increasing number of studies have been proposed to develop deep-learning-based frameworks for medical image segmentation. However, since the pixel-wise annotation of medical images is laborious and expensive, the amount of annotated data is usually deficient to well-train a neural network. In this paper, we propose a semi-supervised approach to train neural networks with limited labeled data and a large quantity of unlabeled images for medical image segmentation. A novel pseudo-label (namely self-loop uncertainty), generated by recurrently optimizing the neural network with a self-supervised task, is adopted as the ground-truth for the unlabeled images to augment the training set and boost the segmentation accuracy. The proposed self-loop uncertainty can be seen as an approximation of the uncertainty estimation yielded by ensembling multiple models with a significant reduction of inference time. Experimental results on two publicly available datasets demonstrate the effectiveness of our semi-supervied approach.

eess.IV↗

arXiv2020

Sams-Net: A Sliced Attention-based Neural Network for Music Source Separation

Convolutional Neural Network (CNN) or Long short-term memory (LSTM) based models with the input of spectrogram or waveforms are commonly used for deep learning based audio source separation. In this paper, we propose a Sliced Attention-based neural network (Sams-Net) in the spectrogram domain for the music source separation task. It enables spectral feature interactions with multi-head attention mechanism, achieves easier parallel computing and has a larger receptive field compared with LSTMs and CNNs respectively. Experimental results on the MUSDB18 dataset show that the proposed method, with fewer parameters, outperforms most of the state-of-the-art DNN-based methods.

eess.AS↗

arXiv2020

Generative Adversarial Networks for Video-to-Video Domain Adaptation

Endoscopic videos from multicentres often have different imaging conditions, e.g., color and illumination, which make the models trained on one domain usually fail to generalize well to another. Domain adaptation is one of the potential solutions to address the problem. However, few of existing works focused on the translation of video-based data. In this work, we propose a novel generative adversarial network (GAN), namely VideoGAN, to transfer the video-based data across different domains. As the frames of a video may have similar content and imaging conditions, the proposed VideoGAN has an X-shape generator to preserve the intra-video consistency during translation. Furthermore, a loss function, namely color histogram loss, is proposed to tune the color distribution of each translated frame. Two colonoscopic datasets from different centres, i.e., CVC-Clinic and ETIS-Larib, are adopted to evaluate the performance of domain adaptation of our VideoGAN. Experimental results demonstrate that the adapted colonoscopic video generated by our VideoGAN can significantly boost the segmentation accuracy, i.e., an improvement of 5%, of colorectal polyps on multicentre datasets. As our VideoGAN is a general network architecture, we also evaluate its performance with the CamVid driving video dataset on the cloudy-to-sunny translation task. Comprehensive experiments show that the domain gap could be substantially narrowed down by our VideoGAN.

cs.CV↗

arXiv2020

A Cyclically-Trained Adversarial Network for Invariant Representation Learning

Recent studies show that deep neural networks are vulnerable to adversarial examples which can be generated via certain types of transformations. Being robust to a desired family of adversarial attacks is then equivalent to being invariant to a family of transformations. Learning invariant representations then naturally emerges as an important goal to achieve which we explore in this paper within specific application contexts. Specifically, we propose a cyclically-trained adversarial network to learn a mapping from image space to latent representation space and back such that the latent representation is invariant to a specified factor of variation (e.g., identity). The learned mapping assures that the synthesized image is not only realistic, but has the same values for unspecified factors (e.g., pose and illumination) as the original image and a desired value of the specified factor. Unlike disentangled representation learning, which requires two latent spaces, one for specified and another for unspecified factors, invariant representation learning needs only one such space. We encourage invariance to a specified factor by applying adversarial training using a variational autoencoder in the image space as opposed to the latent space. We strengthen this invariance by introducing a cyclic training process (forward and backward cycle). We also propose a new method to evaluate conditional generative networks. It compares how well different factors of variation can be predicted from the synthesized, as opposed to real, images. In quantitative terms, our approach attains state-of-the-art performance in experiments spanning three datasets with factors such as identity, pose, illumination or style. Our method produces sharp, high-quality synthetic images with little visible artefacts compared to previous approaches.

cs.CV↗

arXiv2020

Long distance measurement using single soliton microcomb

Dispersive interferometry (DPI) takes a major interest in optical frequency comb (OFC) based long distance laser-based light detection and ranging (LIDAR) for the merits of strong anti-interference ability and long coherent length. However, the mismatch between the repetition rate of OFC and the resolution of optical spectrum acquisition system induces a large dead-zone which is a major obstacle for practical applications. Here, a new DPI LIDAR on the strength of high-repetition-rate soliton microcomb is demonstrated, which reaches a minimum Allan deviation of 27 nm for an outdoor 1179 m ranging experiment. The proposed scheme approaches a compact, high-accuracy, and none-dead-zone long distance ranging system, opening up new opportunities for emerging applications of frontier scientific researches and advanced manufacturing.

physics.ins-det↗

arXiv2020

Fast Adaptively Weighted Matrix Factorization for Recommendation with Implicit Feedback

Recommendation from implicit feedback is a highly challenging task due to the lack of the reliable observed negative data. A popular and effective approach for implicit recommendation is to treat unobserved data as negative but downweight their confidence. Naturally, how to assign confidence weights and how to handle the large number of the unobserved data are two key problems for implicit recommendation models. However, existing methods either pursuit fast learning by manually assigning simple confidence weights, which lacks flexibility and may create empirical bias in evaluating user's preference; or adaptively infer personalized confidence weights but suffer from low efficiency. To achieve both adaptive weights assignment and efficient model learning, we propose a fast adaptively weighted matrix factorization (FAWMF) based on variational auto-encoder. The personalized data confidence weights are adaptively assigned with a parameterized neural network (function) and the network can be inferred from the data. Further, to support fast and stable learning of FAWMF, a new specific batch-based learning algorithm fBGD has been developed, which trains on all feedback data but its complexity is linear to the number of observed data. Extensive experiments on real-world datasets demonstrate the superiority of the proposed FAWMF and its learning algorithm fBGD.

cs.IR↗

arXiv2020

VAE/WGAN-Based Image Representation Learning For Pose-Preserving Seamless Identity Replacement In Facial Images

We present a novel variational generative adversarial network (VGAN) based on Wasserstein loss to learn a latent representation from a face image that is invariant to identity but preserves head-pose information. This facilitates synthesis of a realistic face image with the same head pose as a given input image, but with a different identity. One application of this network is in privacy-sensitive scenarios; after identity replacement in an image, utility, such as head pose, can still be recovered. Extensive experimental validation on synthetic and real human-face image datasets performed under 3 threat scenarios confirms the ability of the proposed network to preserve head pose of the input image, mask the input identity, and synthesize a good-quality realistic face image of a desired identity. We also show that our network can be used to perform pose-preserving identity morphing and identity-preserving pose morphing. The proposed method improves over a recent state-of-the-art method in terms of quantitative metrics as well as synthesized image quality.

cs.CV↗

arXiv2019

A proximal average for prox-bounded functions

In this work, we construct a proximal average for two prox-bounded functions, which recovers the classical proximal average for two convex functions. The new proximal average transforms continuously in epi-topology from one proximal hull to the other. When one of the functions is differentiable, the new proximal average is differentiable. We give characterizations for Lipschitz and single-valued proximal mappings and we show that the convex combination of convexified proximal mappings is always a proximal mapping. Subdifferentiability and behaviors of infimal values and minimizers are also studied.

math.FA↗

arXiv2019

OctopusNet: A Deep Learning Segmentation Network for Multi-modal Medical Images

Deep learning models, such as the fully convolutional network (FCN), have been widely used in 3D biomedical segmentation and achieved state-of-the-art performance. Multiple modalities are often used for disease diagnosis and quantification. Two approaches are widely used in the literature to fuse multiple modalities in the segmentation networks: early-fusion (which stacks multiple modalities as different input channels) and late-fusion (which fuses the segmentation results from different modalities at the very end). These fusion methods easily suffer from the cross-modal interference caused by the input modalities which have wide variations. To address the problem, we propose a novel deep learning architecture, namely OctopusNet, to better leverage and fuse the information contained in multi-modalities. The proposed framework employs a separate encoder for each modality for feature extraction and exploits a hyper-fusion decoder to fuse the extracted features while avoiding feature explosion. We evaluate the proposed OctopusNet on two publicly available datasets, i.e. ISLES-2018 and MRBrainS-2013. The experimental results show that our framework outperforms the commonly-used feature fusion approaches and yields the state-of-the-art segmentation accuracy.

eess.IV↗

arXiv2019

Secure Analysis Over Generalized-K Channels

In this letter, we adopt the SOP definition in [4] and the simplified model of [8], and derive a closed-form expression for the proposed SOP over GK fading channels. To simplify this expression and obtain additional insights, we also perform an asymptotic analysis of the main link in the high SNR region.

eess.SP↗

arXiv2019

HAHE: Hierarchical Attentive Heterogeneous Information Network Embedding

Heterogeneous information network (HIN) embedding has recently attracted much attention due to its effectiveness in dealing with the complex heterogeneous data. Meta path, which connects different object types with various semantic meanings, is widely used by existing HIN embedding works. However, several challenges have not been addressed so far. First, different meta paths convey different semantic meanings, while existing works assume that all nodes share same weights for meta paths and ignore the personalized preferences of different nodes on different meta paths. Second, given a meta path, nodes in HIN are connected by path instances while existing works fail to fully explore the differences between path instances that reflect nodes' preferences in the semantic space. rTo tackle the above challenges, we propose aHierarchical Attentive Heterogeneous information network Embedding (HAHE) model to capture the personalized preferences on meta paths and path instances in each semantic space. As path instances are based on a particular meta path, a hierarchical attention mechanism is naturally utilized to model the personalized preference on meta paths and path instances. Extensive experiments on several real-world datasets show that our proposed \model model significantly outperforms the state-of-the-art methods in terms of various data mining tasks.

cs.SI↗

arXiv2018

Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions

Deep convolutional neural networks (ConvNets) have been recently shown to attain state-of-the-art performance for action recognition on standard-resolution videos. However, less attention has been paid to recognition performance at extremely low resolutions (eLR) (e.g., 16 x 12 pixels). Reliable action recognition using eLR cameras would address privacy concerns in various application environments such as private homes, hospitals, nursing/rehabilitation facilities, etc. In this paper, we propose a semi-coupled filter-sharing network that leverages high resolution (HR) videos during training in order to assist an eLR ConvNet. We also study methods for fusing spatial and temporal ConvNets customized for eLR videos in order to take advantage of appearance and motion information. Our method outperforms state-of-the-art methods at extremely low resolutions on IXMAS (93.7%) and HMDB (29.2%) datasets.

cs.CV↗

arXiv2018

VGAN-Based Image Representation Learning for Privacy-Preserving Facial Expression Recognition

Reliable facial expression recognition plays a critical role in human-machine interactions. However, most of the facial expression analysis methodologies proposed to date pay little or no attention to the protection of a user's privacy. In this paper, we propose a Privacy-Preserving Representation-Learning Variational Generative Adversarial Network (PPRL-VGAN) to learn an image representation that is explicitly disentangled from the identity information. At the same time, this representation is discriminative from the standpoint of facial expression recognition and generative as it allows expression-equivalent face image synthesis. We evaluate the proposed model on two public datasets under various threat scenarios. Quantitative and qualitative results demonstrate that our approach strikes a balance between the preservation of privacy and data utility. We further demonstrate that our model can be effectively applied to other tasks such as expression morphing and image completion.

cs.CV↗

arXiv2017

Tungsten disulfide-gold nanohole hybrid metasurfaces for nonlinear metalens in the visible region

Recently, nonlinear hybrid metasurface comes into an attractive new concept in the research of nanophotonics and nanotechnology. It is composed of semiconductors with an intrinsically large nonlinear susceptibility and traditional plasmonic metasurfaces, offering opportunities for efficiently generating and manipulating nonlinear optical responses. A high second-harmonic generation (SHG) conversion efficiency has been demonstrated in the mid-infrared region by using multi-quantum-well (MQW) based plasmonic metasurfaces. However, it has yet to be demonstrated in the visible region. Here we present a new type of nonlinear hybrid metasurfaces for the visible region, which consists of a single layer of tungsten disulfide (WS2) and a phased gold nanohole array. The results indicate that a large SHG susceptibility of ~0.1 nm/V at 810 nm is achieved, which is 2~3 orders of magnitude larger than that of typical plasmonic metasurfaces. Nonlinear metalenses with the focal lengths of 30 μm, 50 μm and 100 μm are demonstrated experimentally, providing a direct evidence for both generating and manipulating SH signals based on the nonlinear hybrid metasurfaces. It shows great potential applications in designing of integrated, ultra-thin, compacted and efficient nonlinear optical devices, such as frequency converters, nonlinear holography and generation of nonlinear optical vortex beam.

physics.optics↗

arXiv2015

Highly-sensitive detection of the lattice distortion in single bent ZnO nanowires by second-harmonic generation microscopy

Nanogenerators based on ZnO nanowires (NWs) realize the energy conversion at nanoscale, which are ascribed to the piezoelectric property caused by the lattice distortion of the ZnO NWs. The lattice distortion can significantly tune the electronic and optical properties, and requires a sensitive and convenient measurement. However, high-resolution transmission electron microscopy (HRTEM) technique provides a limited sensitivity of 0.01 nm on the variation of the lattice spacing and requires vacuum conditions. Here we demonstrate a highly-sensitive detection of the lattice distortion in single bent ZnO NWs by second-harmonic generation (SHG) microscopy. As the curvature of the single bent ZnO NW increases to 21 mm-1 (<4% bending distortion), it shows a significant decrease (~70%) in the SHG intensity ratio between perpendicular and parallel excitation polarization with respect to c-axis of ZnO NWs. Importantly, the extraordinary non-axisymmetrical SHG polarimetric patterns are also observed, indicating the twisting distortion around c-axis of ZnO NWs. Thus, SHG microscopy provides a sensitive all-optical and non-invasive method for in situ detecting the lattice distortion under various circumstances.

physics.optics↗

arXiv2014

Multiple Hybrid Phase Transition: Bootstrap Percolation on Complex Networks with Communities

Bootstrap percolation is a well-known model to study the spreading of rumors, new products or innovations on social networks. The empirical studies show that community structure is ubiquitous among various social networks. Thus, studying the bootstrap percolation on the complex networks with communities can bring us new and important insights of the spreading dynamics on social networks. It attracts a lot of scientists' attentions recently. In this letter, we study the bootstrap percolation on Erdős-Rényi networks with communities and observed second order, hybrid (both second and first order) and multiple hybrid phase transitions, which is rare in natural system. Moreover, we have analytically solved this system and obtained the phase diagram, which is further justified well by the corresponding simulations.

physics.soc-ph↗

arXiv2014

Building A Large Concept Bank for Representing Events in Video

Concept-based video representation has proven to be effective in complex event detection. However, existing methods either manually design concepts or directly adopt concept libraries not specifically designed for events. In this paper, we propose to build Concept Bank, the largest concept library consisting of 4,876 concepts specifically designed to cover 631 real-world events. To construct the Concept Bank, we first gather a comprehensive event collection from WikiHow, a collaborative writing project that aims to build the world's largest manual for any possible How-To event. For each event, we then search Flickr and discover relevant concepts from the tags of the returned images. We train a Multiple Kernel Linear SVM for each discovered concept as a concept detector in Concept Bank. We organize the concepts into a five-layer tree structure, in which the higher-level nodes correspond to the event categories while the leaf nodes are the event-specific concepts discovered for each event. Based on such tree ontology, we develop a semantic matching method to select relevant concepts for each textual event query, and then apply the corresponding concept detectors to generate concept-based video representations. We use TRECVID Multimedia Event Detection 2013 and Columbia Consumer Video open source event definitions and videos as our test sets and show very promising results on two video event detection tasks: event modeling over concept space and zero-shot event retrieval. To the best of our knowledge, this is the largest concept library covering the largest number of real-world events.

cs.MM↗