Search Results for author:
Found 102 papers, 33 papers with code
Addressing Asymmetry in Multilingual Neural Machine Translation with Fuzzy Task Clustering
However, the existing clustering methods based on language similarity cannot handle the asymmetric problem in multilingual NMT, i. e., one translation task A can benefit from another translation task B but task B will be harmed by task A.
Deep learning reveals the common spectrum underlying multiple brain disorders in youth and elders from brain functional networks
Brain disorders in the early and late life of humans potentially share pathological alterations in brain functions.
ChatCAD: Interactive Computer-Aided Diagnosis on Medical Image using Large Language Models
Large language models (LLMs) have recently demonstrated their potential in clinical applications, providing valuable medical knowledge and advice.
RCPS: Rectified Contrastive Pseudo Supervision for Semi-Supervised Medical Image Segmentation
However, learning a robust representation from numerous unlabeled images remains challenging due to potential noise in pseudo labels and insufficient class separability in feature space, which undermines the performance of current semi-supervised segmentation approaches.
Integrating multi-type aberrations from DNA and RNA through dynamic mapping gene space for subtype-specific breast cancer driver discovery
Notably, cancer driver events would occur due to not only DNA aberrations but also RNA alternations, but integrating multi-type aberrations from both DNA and RNA is still a challenging task for breast cancer drivers.
On Fine-Tuned Deep Features for Unsupervised Domain Adaptation
Prior feature transformation based approaches to Unsupervised Domain Adaptation (UDA) employ the deep features extracted by pre-trained deep models without fine-tuning them on the specific source or target domain data for a particular domain adaptation task.
Probabilistic Generative Transformer Language models for Generative Design of Molecules
Self-supervised neural language models have recently found wide applications in generative design of organic molecules and protein sequences as well as representation learning for downstream structure classification and functional prediction.
TBI-GAN: An Adversarial Learning Approach for Data Synthesis on Traumatic Brain Segmentation
To address these issues, we propose a novel medical image inpainting model named TBI-GAN to synthesize TBI MR scans with paired brain label maps.
Image Synthesis with Disentangled Attributes for Chest X-Ray Nodule Augmentation and Detection
Moreover, we propose to synthesize nodule CXR images by controlling the disentangled nodule attributes for data augmentation, in order to better compensate for the nodules that are easily missed in the detection task.
Dynamic Budget Throttling in Repeated Second-Price Auctions
In the stochastic case, we illustrate that pacing is generally better than throttling for the buyer, which is an extension of known results that pacing is asymptotically optimal in this scenario.
DP$^2$-NILM: A Distributed and Privacy-preserving Framework for Non-intrusive Load Monitoring
Non-intrusive load monitoring (NILM), which usually utilizes machine learning methods and is effective in disaggregating smart meter readings from the household-level into appliance-level consumption, can help analyze electricity consumption behaviours of users and enable practical smart energy and smart grid applications.
Eye-gaze-guided Vision Transformer for Rectifying Shortcut Learning
To address this problem, we propose to infuse human experts' intelligence and domain knowledge into the training of deep neural networks.
Spatial Attention-based Implicit Neural Representation for Arbitrary Reduction of MRI Slice Spacing
Magnetic resonance (MR) images collected in 2D clinical protocols typically have large inter-slice spacing, resulting in high in-plane resolution and reduced through-plane resolution.
Deep Generalized Unfolding Networks for Image Restoration
Concretely, without loss of interpretability, we integrate a gradient estimation strategy into the gradient descent step of the Proximal Gradient Descent (PGD) algorithm, driving it to deal with complex and real-world image degradation.
NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results
This challenge includes three tracks.
Follow My Eye: Using Gaze to Supervise Computer-Aided Diagnosis
In this paper, we demonstrate that the eye movement of radiologists reading medical images can be a new form of supervision to train the DNN-based computer-aided diagnosis (CAD) system.
FairNeuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neurons
To solve this issue, there has been a number of work trying to improve model fairness by using an adversarial game in model level.
Automatic Facial Skin Feature Detection for Everyone
We present an automatic facial skin feature detection method that works across a variety of skin tones and age groups for selfies in the wild.
Towards Benchmarking and Evaluating Deepfake Detection
Deepfake detection automatically recognizes the manipulated medias through the analysis of the difference between manipulated and non-altered videos.
Transformers in Medical Image Analysis: A Review
Transformers have dominated the field of natural language processing, and recently impacted the computer vision area.
Knee Cartilage Defect Assessment by Graph Representation and Surface Convolution
Knee osteoarthritis (OA) is the most common osteoarthritis and a leading cause of disability.
Parameter Differentiation based Multilingual Neural Machine Translation
Further analyses reveal that the parameter sharing configuration obtained by our method correlates well with the linguistic proximities.
Learning Hierarchical Attention for Weakly-supervised Chest X-Ray Abnormality Localization and Diagnosis
However, doing this accurately will require a large amount of disease localization annotations by clinical experts, a task that is prohibitively expensive to accomplish for most applications.
Reconstructing Training Data from Diverse ML Models by Ensemble Inversion
This technique leads to noticeable improvements of the quality of the generated samples with distinguishable features of the dataset entities compared to MI of a single ML model.
Progressively Select and Reject Pseudo-labelled Samples for Open-Set Domain Adaptation
The common subspace learning algorithm OSLPP simultaneously aligns the labelled source data and pseudo-labelled target data from known classes and pushes the rejected target data away from the known classes.
Black-box Adversarial Attacks on Commercial Speech Platforms with Minimal Information
For commercial cloud speech APIs, we propose Occam, a decision-only black-box adversarial attack, where only final decisions are available to the adversary.
Unsupervised Landmark Detection Based Spatiotemporal Motion Estimation for 4D Dynamic Medical Images
In the first stage, we process the raw dense image to extract sparse landmarks to represent the target organ anatomical topology and discard the redundant information that is unnecessary for motion estimation.
Digital Twins based Day-ahead Integrated Energy System Scheduling under Load and Renewable Energy Uncertainties
By constructing digital twins (DT) of an integrated energy system (IES), one can benefit from DT's predictive capabilities to improve coordinations among various energy converters, hence enhancing energy efficiency, cost savings and carbon emission reduction.
Multi-Modal MRI Reconstruction Assisted with Spatial Alignment Network
However, we find that the performance of the aforementioned multi-modal reconstruction can be negatively affected by subtle spatial misalignment between different modalities, which is actually common in clinical practice.
FederatedNILM: A Distributed and Privacy-preserving Framework for Non-intrusive Load Monitoring based on Federated Deep Learning
Non-intrusive load monitoring (NILM), which usually utilizes machine learning methods and is effective in disaggregating smart meter readings from the household-level into appliance-level consumptions, can help to analyze electricity consumption behaviours of users and enable practical smart energy and smart grid applications.
Electrical peak demand forecasting- A review
To this end, this paper provides a timely and comprehensive overview of peak load demand forecast methods in the literature.
Intrusion Detection and Localization for Networked Embedded Control Systems
In this paper we present a physics-based Intrusion Detection System (IDS) aimed at increasing the security in control systems.
CARTL: Cooperative Adversarially-Robust Transfer Learning
In deep learning, a typical strategy for transfer learning is to freeze the early layers of a pre-trained model and fine-tune the rest of its layers on the target domain.
FedSup: A Communication-Efficient Federated Learning Fatigue Driving Behaviors Supervision Framework
With the proliferation of edge smart devices and the Internet of Vehicles (IoV) technologies, intelligent fatigue detection has become one of the most-used methods in our daily driving.
How to distribute data across tasks for meta-learning?
We show that: 1) If tasks are homogeneous, there is a uniform optimal allocation, whereby all tasks get the same amount of data; 2) At fixed budget, there is a trade-off between number of tasks and number of data points per task, with a unique solution for the optimum; 3) When trained separately, harder task should get more data, at the cost of a smaller number of tasks; 4) When training on a mixture of easy and hard tasks, more data should be allocated to easy tasks.
A bottom-up quantification of flexibility potential from the thermal energy storage in electric space heating
To this end, dwellings with heat pumps and direct electric heaters are modeled as thermal energy storage equivalents that can be included in a linear two-stage problem formulation.
Modularity and Mutual Information in Networks: Two Sides of the Same Coin
At a high level, we show the significance of community structure is equivalent to the amount of information contained in the network.
Community Detection
Social and Information Networks
DeepCervix: A Deep Learning-based Framework for the Classification of Cervical Cells Using Hybrid Deep Feature Fusion Techniques
Pap smear test is a widely performed screening technique for early detection of cervical cancer, whereas this manual screening method suffers from high false-positive results because of human errors.
Recent Advances in Adversarial Training for Adversarial Robustness
Adversarial training is one of the most effective approaches defending against adversarial examples for deep learning models.
Contraband Materials Detection Within Volumetric 3D Computed Tomography Baggage Security Screening Imagery
Specifically, we formulate it as a 3D semantic segmentation problem to identify material types for all voxels based on which contraband materials can be detected.
Touch Editing: A Flexible One-Time Interaction Approach for Translation
We propose a touch-based editing method for translation, which is more flexible than traditional keyboard-mouse-based translation postediting.
Data Augmentation with norm-VAE for Unsupervised Domain Adaptation
As a result, our proposed methods (i. e. naive-SPL and norm-VAE-SPL) can achieve new state-of-the-art performance with the average accuracy of 93. 4% and 90. 4% on Office-Caltech and ImageCLEF-DA datasets, and comparable performance on Digits, Office31 and Office-Home datasets with the average accuracy of 97. 2%, 87. 6% and 67. 9% respectively.
A Comprehensive Review for MRF and CRF Approaches in Pathology Image Analysis
In this review, we present a comprehensive overview of pathology image analysis based on the markov random fields (MRFs) and conditional random fields (CRFs), which are two popular random field models.
Collaborative Fairness in Federated Learning
In current deep learning paradigms, local training or the Standalone framework tends to result in overfitting and thus poor generalizability.
Generalized Zero-Shot Domain Adaptation via Coupled Conditional Variational Autoencoders
In this paper, we formulate this particular domain adaptation problem within a generalized zero-shot learning framework by treating the labelled source domain samples as semantic representations for zero-shot learning.
Multi-Class 3D Object Detection Within Volumetric 3D Computed Tomography Baggage Security Screening Imagery
X-ray Computed Tomography (CT) based 3D imaging is widely used in airports for aviation security screening whilst prior work on automatic prohibited item detection focus primarily on 2D X-ray imagery.
Learning Error-Driven Curriculum for Crowd Counting
Density regression has been widely employed in crowd counting.
Optimizing Information Freshness in Two-Hop Status Update Systems under a Resource Constraint
We derive approximate closed-form expressions of the average AoI at the destination, and the average number of forwarding operations at the relay for the DTR policy, by modelling the tangled evolution of age at relay and destination as a Markov chain (MC).
Information Theory Networking and Internet Architecture Signal Processing Information Theory
CASIA's System for IWSLT 2020 Open Domain Translation
This paper describes the CASIA{'}s system for the IWSLT 2020 open domain translation task.
mr2NST: Multi-Resolution and Multi-Reference Neural Style Transfer for Mammography
However, the image styles of different vendors are very distinctive, and there may exist domain gap among different vendors that could potentially compromise the universal applicability of one deep learning model.
A Self-ensembling Framework for Semi-supervised Knee Cartilage Defects Assessment with Dual-Consistency
With dual-consistency checking of the attention in the lesion classification and localization, the two networks can gradually optimize the attention distribution and improve the performance of each other, whereas the training relies on partially labeled data only and follows the semi-supervised manner.
An Auto-Context Deformable Registration Network for Infant Brain MRI
Deformable image registration is fundamental to longitudinal and population analysis.
Dual-Sampling Attention Network for Diagnosis of COVID-19 from Community Acquired Pneumonia
To this end, we develop a dual-sampling attention network to automatically diagnose COVID- 19 from the community acquired pneumonia (CAP) in chest computed tomography (CT).
Cross-Domain Structure Preserving Projection for Heterogeneous Domain Adaptation
Heterogeneous Domain Adaptation (HDA) addresses the transfer learning problems where data from the source and target domains are of different modalities (e. g., texts and images) or feature dimensions (e. g., features extracted with different methods).
Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation and Diagnosis for COVID-19
In this review paper, we thus cover the entire pipeline of medical imaging and analysis techniques involved with COVID-19, including image acquisition, segmentation, diagnosis, and follow-up.
On the Evaluation of Prohibited Item Classification and Detection in Volumetric 3D Computed Tomography Baggage Security Screening Imagery
As the first attempt to use 3D CNN for volumetric 3D CT baggage security screening, we first evaluate different CNN architectures on the classification of isolated prohibited item volumes and compare against traditional methods which use hand-crafted features.
Reducing Magnetic Resonance Image Spacing by Learning Without Ground-Truth
In this work, we propose a novel deep-learning-based super-resolution algorithm to generate high-resolution (HR) MR images with small slice spacing from low-resolution (LR) inputs of large slice spacing.
A Comprehensive Review for Breast Histopathology Image Analysis Using Classical and Deep Neural Networks
Breast cancer is one of the most common and deadliest cancers among women.
Generalized logistic growth modeling of the COVID-19 outbreak in 29 provinces in China and in the rest of the world
Japan and Italy are in serious situations with no short-term end to the outbreak to be expected.
Populations and Evolution Biological Physics Applications
A Spatiotemporal Volumetric Interpolation Network for 4D Dynamic Medical Image
SVIN introduces dual networks: first is the spatiotemporal motion network that leverages the 3D convolutional neural network (CNN) for unsupervised parametric volumetric registration to derive spatiotemporal motion field from two-image volumes; the second is the sequential volumetric interpolation network, which uses the derived motion field to interpolate image volumes, together with a new regression-based module to characterize the periodic motion cycles in functional organ structures.
Optimizing Privacy-Preserving Outsourced Convolutional Neural Network Predictions
This paper proposes a new scheme for privacy-preserving neural network prediction in the outsourced setting, i. e., the server cannot learn the query, (intermediate) results, and the model.
A Reference Architecture for Plausible Threat Image Projection (TIP) Within 3D X-ray Computed Tomography Volumes
Threat Image Projection (TIP) is a technique used in X-ray security baggage screening systems that superimposes a threat object signature onto a benign X-ray baggage image in a plausible and realistic manner.
Robust Brain Magnetic Resonance Image Segmentation for Hydrocephalus Patients: Hard and Soft Attention
Brain magnetic resonance (MR) segmentation for hydrocephalus patients is considered as a challenging work.
Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling
Unsupervised domain adaptation aims to address the problem of classifying unlabeled samples from the target domain whilst labeled samples are only available from the source domain and the data distributions are different in these two domains.
Ranked #1 on
Domain Adaptation
on Office-Caltech
Crowd Counting via Segmentation Guided Attention Networks and Curriculum Loss
Automatic crowd behaviour analysis is an important task for intelligent transportation systems to enable effective flow control and dynamic route planning for varying road participants.
Ranked #2 on
Crowd Counting
on ShanghaiTech B
Shielding Collaborative Learning: Mitigating Poisoning Attacks through Client-Side Detection
Collaborative learning allows multiple clients to train a joint model without sharing their data with each other.
An End-to-End Network for Co-Saliency Detection in One Single Image
Co-saliency detection within a single image is a common vision problem that has received little attention and has not yet been well addressed.
The Good, the Bad and the Ugly: Evaluating Convolutional Neural Networks for Prohibited Item Detection Using Real and Synthetically Composited X-ray Imagery
This work opens up the possibility of using synthetically composed imagery, avoiding the need to collate such large volumes of hand-annotated real-world imagery.
NCLS: Neural Cross-Lingual Summarization
Moreover, we propose to further improve NCLS by incorporating two related tasks, monolingual summarization and machine translation, into the training process of CLS under multi-task learning.
advPattern: Physical-World Attacks on Deep Person Re-Identification via Adversarially Transformable Patterns
The results demonstrate that deep re-ID systems are vulnerable to our physical attacks.
Synthesis and Inpainting-Based MR-CT Registration for Image-Guided Thermal Ablation of Liver Tumors
Then, an unsupervised registration network is used to efficiently align the pre-procedural CT (pCT) with the inpainted iCT (inpCT) image.
Dual Adversarial Learning with Attention Mechanism for Fine-grained Medical Image Synthesis
To address this issue, we propose a simple but effective strategy, that is, we propose a dual-discriminator (dual-D) adversarial learning system, in which, a global-D is used to make an overall evaluation for the synthetic image, and a local-D is proposed to densely evaluate the local regions of the synthetic image.
Brain MR Image Segmentation in Small Dataset with Adversarial Defense and Task Reorganization
Medical image segmentation is challenging especially in dealing with small dataset of 3D MR images.
Task Decomposition and Synchronization for Semantic Biomedical Image Segmentation
In this paper, we propose to decompose the single segmentation task into three subsequent sub-tasks, including (1) pixel-wise image segmentation, (2) prediction of the class labels of the objects within the image, and (3) classification of the scene the image belonging to.
DLIMD: Dictionary Learning based Image-domain Material Decomposition for spectral CT
Second, we employ the direct inversion (DI) method to obtain initial material decomposition results, and a set of image patches are extracted from the mode-1 unfolding of normalized material image tensor to train a united dictionary by the K-SVD technique.
Unifying Unsupervised Domain Adaptation and Zero-Shot Visual Recognition
Unsupervised domain adaptation aims to transfer knowledge from a source domain to a target domain so that the target domain data can be recognized without any explicit labelling information for this domain.
Ranked #3 on
Domain Adaptation
on Office-Caltech
Generalized Zero-Shot Learning
Unsupervised Domain Adaptation
An Approach for Adaptive Automatic Threat Recognition Within 3D Computed Tomography Images for Baggage Security Screening
To address this issue, the concept of adaptive automatic threat recognition (AATR) was proposed in previous work.
Robust Lane Detection from Continuous Driving Scenes Using Deep Neural Networks
Specifically, information of each frame is abstracted by a CNN block, and the CNN features of multiple continuous frames, holding the property of time-series, are then fed into the RNN block for feature learning and lane prediction.
Automated Segmentation of the Optic Disk and Cup using Dual-Stage Fully Convolutional Networks
Our approach leverages deep residual architectures and FCNs and learns and infers the location of the optic cup and disk in a step-wise manner with fine-grained details.
Deep Morphological Simplification Network (MS-Net) for Guided Registration of Brain Magnetic Resonance Images
Thus, the two trajectories can act as a bridge to link the fixed and the moving images, and guide their registration.
Privacy-Preserving Collaborative Deep Learning with Unreliable Participants
With powerful parallel computing GPUs and massive user data, neural-network-based deep learning can well exert its strong power in problem modeling and solving, and has archived great success in many applications such as image classification, speech recognition and machine translation etc.
Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning
Although the state-of-the-art attacking techniques that incorporated the advance of Generative adversarial networks (GANs) could construct class representatives of the global data distribution among all clients, it is still challenging to distinguishably attack a specific client (i. e., user-level privacy leakage), which is a stronger privacy threat to precisely recover the private data from a specific client.
A Baseline for Multi-Label Image Classification Using An Ensemble of Deep Convolutional Neural Networks
Recent studies on multi-label image classification have focused on designing more complex architectures of deep neural networks such as the use of attention mechanisms and region proposal networks.
Watermark Retrieval from 3D Printed Objects via Convolutional Neural Networks
We present a method for reading digital data embedded in planar 3D printed surfaces.
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
Deep Learning-Based Gait Recognition Using Smartphones in the Wild
Specifically, a hybrid deep neural network is proposed for robust gait feature representation, where features in the space and time domains are successively abstracted by a convolutional neural network and a recurrent neural network.
Block Matching Frame based Material Reconstruction for Spectral CT
Spectral computed tomography (CT) has a great potential in material identification and decomposition.
Dating Ancient Paintings of Mogao Grottoes Using Deeply Learnt Visual Codes
Cultural heritage is the asset of all the peoples of the world.
Supervised and Semi-Supervised Deep Neural Networks for CSI-Based Authentication
In addition, we propose to use the convolutional recurrent neural network (CRNN)---a combination of the CNN and the RNN---to learn local and contextual information in CSI for user authentication.
Non-local Low-rank Cube-based Tensor Factorization for Spectral CT Reconstruction
Then, as a new regularizer, Kronecker-Basis-Representation (KBR) tensor factorization is employed into a basic spectral CT reconstruction model to enhance the ability of extracting image features and protecting spatial edges, generating the non-local low-rank cube-based tensor factorization (NLCTF) method.
Deep Learning based Inter-Modality Image Registration Supervised by Intra-Modality Similarity
In this paper, we propose to train a non-rigid inter-modality image registration network, which can directly predict the transformation field from the input multimodal images, such as CT and MR images.
Medical Image Synthesis with Deep Convolutional Adversarial Networks
To better model a nonlinear mapping from source to target and to produce more realistic target images, we propose to use the adversarial learning strategy to better model the FCN.
Low-dose spectral CT reconstruction using L0 image gradient and tensor dictionary
The L0TDL method inherits the advantages of tensor dictionary learning (TDL) by employing the similarity of spectral CT images.
Multi-Label Zero-Shot Human Action Recognition via Joint Latent Ranking Embedding
Our framework holistically tackles the issue of unknown temporal boundaries between different actions for multi-label learning and exploits the side information regarding the semantic relationship between different human actions for knowledge transfer.
Deep Embedding Convolutional Neural Network for Synthesizing CT Image from T1-Weighted MR Image
After repeat-ing this embedding procedure for several times in the network, we can eventually synthesize a final CT image in the end of the DECNN.
Alternative Semantic Representations for Zero-Shot Human Action Recognition
A proper semantic representation for encoding side information is key to the success of zero-shot learning.
Ranked #14 on
Zero-Shot Action Recognition
on UCF101
Real-time Traffic Accident Risk Prediction based on Frequent Pattern Tree
Both the proposed method based on the FP tree algorithm, as well as the widely utilized, random forest method, were then used to identify the important variables or the Virginia dataset.
Robust Gait Recognition by Integrating Inertial and RGBD Sensors
We propose two new algorithms, namely EigenGait and TrajGait, to extract gait features from the inertial data and the RGBD (color and depth) data, respectively.
Who Leads the Clothing Fashion: Style, Color, or Texture? A Computational Study
Specifically, a classification-based model is proposed to quantify the influence of different visual stimuli, in which each visual stimulus's influence is quantified by its corresponding accuracy in fashion classification.
Zero-Shot Visual Recognition via Bidirectional Latent Embedding
In the top-down stage, semantic representations of unseen-class labels in a given label vocabulary are then embedded to the same latent space to preserve the semantic relatedness between all different classes via our proposed semi-supervised Sammon mapping with the guidance of landmarks.
Attentional Neural Network: Feature Selection Using Cognitive Feedback
Attentional Neural Network is a new framework that integrates top-down cognitive bias and bottom-up feature extraction in one coherent architecture.
Groupwise Registration via Graph Shrinkage on the Image Manifold
Specifically, we first use a graph to model the distribution of all image data sitting on the image manifold, with each node representing an image and each edge representing the geodesic pathway between two nodes (or images).
