arXiv subjects

Junyang Chen

Publications and source records attributed to Junyang Chen.

50 records · Page 3Linked to original sources

arXiv2022

Hybrid Reinforced Medical Report Generation with M-Linear Attention and Repetition Penalty

To reduce doctors' workload, deep-learning-based automatic medical report generation has recently attracted more and more research efforts, where deep convolutional neural networks (CNNs) are employed to encode the input images, and recurrent neural networks (RNNs) are used to decode the visual features into medical reports automatically. However, these state-of-the-art methods mainly suffer from three shortcomings: (i) incomprehensive optimization, (ii) low-order and unidimensional attention mechanisms, and (iii) repeated generation. In this article, we propose a hybrid reinforced medical report generation method with m-linear attention and repetition penalty mechanism (HReMRG-MR) to overcome these problems. Specifically, a hybrid reward with different weights is employed to remedy the limitations of single-metric-based rewards. We also propose a search algorithm with linear complexity to approximate the best weight combination. Furthermore, we use m-linear attention modules to explore high-order feature interactions and to achieve multi-modal reasoning, while a repetition penalty applies penalties to repeated terms during the model's training process. Extensive experimental studies on two public datasets show that HReMRG-MR greatly outperforms the state-of-the-art baselines in terms of all metrics. We also conducted a series of ablation experiments to prove the effectiveness of all our proposed components. We also performed a reward search toy experiment to give evidence that our proposed search approach can significantly reduce the search time while approximating the best performance.

cs.AI↗

arXiv2022

MV-HAN: A Hybrid Attentive Networks based Multi-View Learning Model for Large-scale Contents Recommendation

Industrial recommender systems usually employ multi-source data to improve the recommendation quality, while effectively sharing information between different data sources remain a challenge. In this paper, we introduce a novel Multi-View Approach with Hybrid Attentive Networks (MV-HAN) for contents retrieval at the matching stage of recommender systems. The proposed model enables high-order feature interaction from various input features while effectively transferring knowledge between different types. By employing a well-placed parameters sharing strategy, the MV-HAN substantially improves the retrieval performance in sparse types. The designed MV-HAN inherits the efficiency advantages in the online service from the two-tower model, by mapping users and contents of different types into the same features space. This enables fast retrieval of similar contents with an approximate nearest neighbor algorithm. We conduct offline experiments on several industrial datasets, demonstrating that the proposed MV-HAN significantly outperforms baselines on the content retrieval tasks. Importantly, the MV-HAN is deployed in a real-world matching system. Online A/B test results show that the proposed method can significantly improve the quality of recommendations.

cs.IR↗

arXiv2022

DnSwin: Toward Real-World Denoising via Continuous Wavelet Sliding-Transformer

Real-world image denoising is a practical image restoration problem that aims to obtain clean images from in-the-wild noisy inputs. Recently, the Vision Transformer (ViT) has exhibited a strong ability to capture long-range dependencies, and many researchers have attempted to apply the ViT to image denoising tasks. However, a real-world image is an isolated frame that makes the ViT build long-range dependencies based on the internal patches, which divides images into patches, disarranges noise patterns and damages gradient continuity. In this article, we propose to resolve this issue by using a continuous Wavelet Sliding-Transformer that builds frequency correspondences under real-world scenes, called DnSwin. Specifically, we first extract the bottom features from noisy input images by using a convolutional neural network (CNN) encoder. The key to DnSwin is to extract high-frequency and low-frequency information from the observed features and build frequency dependencies. To this end, we propose a Wavelet Sliding-Window Transformer (WSWT) that utilizes the discrete wavelet transform (DWT), self-attention and the inverse DWT (IDWT) to extract deep features. Finally, we reconstruct the deep features into denoised images using a CNN decoder. Both quantitative and qualitative evaluations conducted on real-world denoising benchmarks demonstrate that the proposed DnSwin performs favorably against the state-of-the-art methods.

cs.CV↗

arXiv2021

Large field-like torque in amorphous Ru2Sn3 originated from the intrinsic spin Hall effect

We investigated temperature dependent current driven spin-orbit torques in magnetron sputtered Ru2Sn3 (4 and 10 nm) /Co20Fe60B20 (5 nm) layered structures with in-plane magnetic anisotropy. The room temperature damping-like and field-like spin torque efficiencies of the amorphous Ru2Sn3 films were measured to be 0.14 +- 0.008 (0.07 +- 0.012) and -0.03 +- 0.006 (-0.20 +- 0.009), for the 4 (10 nm) films respectively, by utilizing the second harmonic Hall technique. The large field-like torque in the relatively thicker Ru2Sn3 (10 nm) thin film is unique compared to the traditional spin Hall materials interfaced with thick magnetic layers with in-plane magnetic anisotropy which typically have dominant damping-like and negligible field-like torques. Additionally, the observed room temperature field-like torque efficiency in Ru2Sn3 (10 nm)/CoFeB (5 nm) is up to three times larger than the damping-like torque (-0.20 +- 0.009 and 0.07 +- 0.012, respectively) and thirty times larger at 50 K (-0.29 +- 0.014 and 0.009 +- 0.017, respectively). The temperature dependence of the field-like torques show dominant contributions from the intrinsic spin Hall effect while the damping-like torques show dominate contributions from the extrinsic spin Hall effects, skew scattering and side jump. Through macro-spin calculations, we found that including field-like torques on the order or larger than the damping-like torque can reduce the switching critical current and decrease magnetization procession for a perpendicular ferromagnetic layer.

cond-mat.mes-hall↗

arXiv2021

A Unified Joint Maximum Mean Discrepancy for Domain Adaptation

Domain adaptation has received a lot of attention in recent years, and many algorithms have been proposed with impressive progress. However, it is still not fully explored concerning the joint probability distribution (P(X, Y)) distance for this problem, since its empirical estimation derived from the maximum mean discrepancy (joint maximum mean discrepancy, JMMD) will involve complex tensor-product operator that is hard to manipulate. To solve this issue, this paper theoretically derives a unified form of JMMD that is easy to optimize, and proves that the marginal, class conditional and weighted class conditional probability distribution distances are our special cases with different label kernels, among which the weighted class conditional one not only can realize feature alignment across domains in the category level, but also deal with imbalance dataset using the class prior probabilities. From the revealed unified JMMD, we illustrate that JMMD degrades the feature-label dependence (discriminability) that benefits to classification, and it is sensitive to the label distribution shift when the label kernel is the weighted class conditional one. Therefore, we leverage Hilbert Schmidt independence criterion and propose a novel MMD matrix to promote the dependence, and devise a novel label kernel that is robust to label distribution shift. Finally, we conduct extensive experiments on several cross-domain datasets to demonstrate the validity and effectiveness of the revealed theoretical results.

cs.LG↗

arXiv2020

SAG-GAN: Semi-Supervised Attention-Guided GANs for Data Augmentation on Medical Images

Recently deep learning methods, in particular, convolutional neural networks (CNNs), have led to a massive breakthrough in the range of computer vision. Also, the large-scale annotated dataset is the essential key to a successful training procedure. However, it is a huge challenge to get such datasets in the medical domain. Towards this, we present a data augmentation method for generating synthetic medical images using cycle-consistency Generative Adversarial Networks (GANs). We add semi-supervised attention modules to generate images with convincing details. We treat tumor images and normal images as two domains. The proposed GANs-based model can generate a tumor image from a normal image, and in turn, it can also generate a normal image from a tumor image. Furthermore, we show that generated medical images can be used for improving the performance of ResNet18 for medical image classification. Our model is applied to three limited datasets of tumor MRI images. We first generate MRI images on limited datasets, then we trained three popular classification models to get the best model for tumor classification. Finally, we train the classification model using real images with classic data augmentation methods and classification models using synthetic images. The classification results between those trained models showed that the proposed SAG-GAN data augmentation method can boost Accuracy and AUC compare with classic data augmentation methods. We believe the proposed data augmentation method can apply to other medical image domains, and improve the accuracy of computer-assisted diagnosis.

eess.IV↗

arXiv2020

Efficient Medical Image Segmentation with Intermediate Supervision Mechanism

Because the expansion path of U-Net may ignore the characteristics of small targets, intermediate supervision mechanism is proposed. The original mask is also entered into the network as a label for intermediate output. However, U-Net is mainly engaged in segmentation, and the extracted features are also targeted at segmentation location information, and the input and output are different. The label we need is that the input and output are both original masks, which is more similar to the refactoring process, so we propose another intermediate supervision mechanism. However, the features extracted by the contraction path of this intermediate monitoring mechanism are not necessarily consistent. For example, U-Net's contraction path extracts transverse features, while auto-encoder extracts longitudinal features, which may cause the output of the expansion path to be inconsistent with the label. Therefore, we put forward the intermediate supervision mechanism of shared-weight decoder module. Although the intermediate supervision mechanism improves the segmentation accuracy, the training time is too long due to the extra input and multiple loss functions. For one of these problems, we have introduced tied-weight decoder. To reduce the redundancy of the model, we combine shared-weight decoder module with tied-weight decoder module.

eess.IV↗

arXiv2020

w-Net: Dual Supervised Medical Image Segmentation Model with Multi-Dimensional Attention and Cascade Multi-Scale Convolution

Deep learning-based medical image segmentation technology aims at automatic recognizing and annotating objects on the medical image. Non-local attention and feature learning by multi-scale methods are widely used to model network, which drives progress in medical image segmentation. However, those attention mechanism methods have weakly non-local receptive fields' strengthened connection for small objects in medical images. Then, the features of important small objects in abstract or coarse feature maps may be deserted, which leads to unsatisfactory performance. Moreover, the existing multi-scale methods only simply focus on different sizes of view, whose sparse multi-scale features collected are not abundant enough for small objects segmentation. In this work, a multi-dimensional attention segmentation model with cascade multi-scale convolution is proposed to predict accurate segmentation for small objects in medical images. As the weight function, multi-dimensional attention modules provide coefficient modification for significant/informative small objects features. Furthermore, The cascade multi-scale convolution modules in each skip-connection path are exploited to capture multi-scale features in different semantic depth. The proposed method is evaluated on three datasets: KiTS19, Pancreas CT of Decathlon-10, and MICCAI 2018 LiTS Challenge, demonstrating better segmentation performances than the state-of-the-art baselines.

cs.CV↗

arXiv2020

Joint Self-Attention and Scale-Aggregation for Self-Calibrated Deraining Network

In the field of multimedia, single image deraining is a basic pre-processing work, which can greatly improve the visual effect of subsequent high-level tasks in rainy conditions. In this paper, we propose an effective algorithm, called JDNet, to solve the single image deraining problem and conduct the segmentation and detection task for applications. Specifically, considering the important information on multi-scale features, we propose a Scale-Aggregation module to learn the features with different scales. Simultaneously, Self-Attention module is introduced to match or outperform their convolutional counterparts, which allows the feature aggregation to adapt to each channel. Furthermore, to improve the basic convolutional feature transformation process of Convolutional Neural Networks (CNNs), Self-Calibrated convolution is applied to build long-range spatial and inter-channel dependencies around each spatial location that explicitly expand fields-of-view of each convolutional layer through internal communications and hence enriches the output features. By designing the Scale-Aggregation and Self-Attention modules with Self-Calibrated convolution skillfully, the proposed model has better deraining results both on real-world and synthetic datasets. Extensive experiments are conducted to demonstrate the superiority of our method compared with state-of-the-art methods. The source code will be available at \url{https://supercong94.wixsite.com/supercong94}.

cs.CV↗

arXiv2020

DCSFN: Deep Cross-scale Fusion Network for Single Image Rain Removal

Rain removal is an important but challenging computer vision task as rain streaks can severely degrade the visibility of images that may make other visions or multimedia tasks fail to work. Previous works mainly focused on feature extraction and processing or neural network structure, while the current rain removal methods can already achieve remarkable results, training based on single network structure without considering the cross-scale relationship may cause information drop-out. In this paper, we explore the cross-scale manner between networks and inner-scale fusion operation to solve the image rain removal task. Specifically, to learn features with different scales, we propose a multi-sub-networks structure, where these sub-networks are fused via a crossscale manner by Gate Recurrent Unit to inner-learn and make full use of information at different scales in these sub-networks. Further, we design an inner-scale connection block to utilize the multi-scale information and features fusion way between different scales to improve rain representation ability and we introduce the dense block with skip connection to inner-connect these blocks. Experimental results on both synthetic and real-world datasets have demonstrated the superiority of our proposed method, which outperforms over the state-of-the-art methods. The source code will be available at https://supercong94.wixsite.com/supercong94.

cs.CV↗

arXiv2020

NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results

This paper reviews the NTIRE 2020 challenge on real world super-resolution. It focuses on the participating methods and final results. The challenge addresses the real world setting, where paired true high and low-resolution images are unavailable. For training, only one set of source input images is therefore provided along with a set of unpaired high-quality target images. In Track 1: Image Processing artifacts, the aim is to super-resolve images with synthetically generated image processing artifacts. This allows for quantitative benchmarking of the approaches \wrt a ground-truth image. In Track 2: Smartphone Images, real low-quality smart phone images have to be super-resolved. In both tracks, the ultimate goal is to achieve the best perceptual quality, evaluated using a human study. This is the second challenge on the subject, following AIM 2019, targeting to advance the state-of-the-art in super-resolution. To measure the performance we use the benchmark protocol from AIM 2019. In total 22 teams competed in the final testing phase, demonstrating new and innovative solutions to the problem.

eess.IV↗

arXiv2020

D2D-Enabled Data Sharing for Distributed Machine Learning at Wireless Network Edge

Mobile edge learning is an emerging technique that enables distributed edge devices to collaborate in training shared machine learning models by exploiting their local data samples and communication and computation resources. To deal with the straggler dilemma issue faced in this technique, this paper proposes a new device to device enabled data sharing approach, in which different edge devices share their data samples among each other over communication links, in order to properly adjust their computation loads for increasing the training speed. Under this setup, we optimize the radio resource allocation for both data sharing and distributed training, with the objective of minimizing the total training delay under fixed numbers of local and global iterations. Numerical results show that the proposed data sharing design significantly reduces the training delay, and also enhances the training accuracy when the data samples are non independent and identically distributed among edge devices.

eess.SP↗

arXiv2019

Magnetic order induced polarization anomaly of Raman scattering in 2D magnet CrI$_3$

The recent discovery of 2D magnets has revealed various intriguing phenomena due to the coupling between spin and other degree of freedoms (such as helical photoluminescence, nonreciprocal SHG). Previous research on the spin-phonon coupling effect mainly focuses on the renormalization of phonon frequency. Here we demonstrate that the Raman polarization selection rules of optical phonons can be greatly modified by the magnetic ordering in 2D magnet CrI$_3$. For monolayer samples, the dominant A$\rm_{1g}$ peak shows abnormally high intensity in the cross polarization channel at low temperature, which is forbidden by the selection rule based on the lattice symmetry. While for bilayer, this peak is absent in the cross polarization channel for the layered antiferromagnetic (AFM) state and reappears when it is tuned to the ferromagnetic (FM) state by an external magnetic field. Our findings shed light on exploring the emergent magneto-optical effects in 2D magnets.

cond-mat.mes-hall↗

arXiv2016

The role of electron and phonon temperatures in the helicity-independent all-optical switching of GdFeCo

Ultrafast optical heating of the electrons in ferrimagnetic metals can result in all-optical switching (AOS) of the magnetization. Here we report quantitative measurements of the temperature rise of GdFeCo thin films during helicity-independent AOS. Critical switching fluences are obtained as a function of the initial temperature of the sample and for laser pulse durations from 55 fs to 15 ps. We conclude that non-equilibrium phenomena are necessary for helicity-independent AOS, although the peak electron temperature does not play a critical role. Pump-probe time-resolved experiments show that the switching time increases as the pulse duration increases, with 10 ps pulses resulting in switching times of ~sim 13 ps. These results raise new questions about the fundamental mechanism of helicity-independent AOS.

cond-mat.mes-hall↗