Search Results for author:
Found 80 papers, 6 papers with code
Confidence Regularized Self-Training
Recent advances in domain adaptation show that deep self-training presents a powerful means for unsupervised domain adaptation.
Ranked #16 on
Domain Adaptation
on VisDA2017
Bathymetry Inversion using a Deep-Learning-Based Surrogate for Shallow Water Equations Solvers
We also found the surrogate architecture (whether with both velocity and water surface elevation or velocity only as outputs) does not show significant impact on inversion result.
Infrared Image Super-Resolution: Systematic Review, and Future Trends
Image Super-Resolution (SR) is essential for a wide range of computer vision and image processing tasks.
Surrogate Model for Shallow Water Equations Solvers with Deep Learning
The new method was evaluated and compared against existing methods based on convolutional neural networks (CNNs), which can only make image-to-image predictions on structured or regular meshes.
Target-oriented Domain Adaptation for Infrared Image Super-Resolution
DASRGAN operates on the synergy of two key components: 1) Texture-Oriented Adaptation (TOA) to refine texture details meticulously, and 2) Noise-Oriented Adaptation (NOA), dedicated to minimizing noise transfer.
Loop Improvement: An Efficient Approach for Extracting Shared Features from Heterogeneous Data without Central Server
LI integrates a loop topology with layer-wise and end-to-end training, compatible with various neural network models.
Contextual-based Image Inpainting: Infer, Match, and Translate
We study the task of image inpainting, which is to fill in the missing region of an incomplete image with plausible contents.
Image Inpainting using Block-wise Procedural Training with Annealed Adversarial Counterpart
We present a new approach to address the difficulty of training a very deep generative model to synthesize high-quality photo-realistic inpainting.
Fast Online Clustering with Randomized Skeleton Sets
To achieve fast clustering, we propose to represent each cluster by a skeleton set which is updated continuously as new data is seen.
PNS: Population-Guided Novelty Search for Reinforcement Learning in Hard Exploration Environments
To balance exploration and exploitation, the Novelty Search (NS) is employed in every chief agent to encourage policies with high novelty while maximizing per-episode performance.
Feature-Level Frankenstein: Eliminating Variations for Discriminative Recognition
Recent successes of deep learning-based recognition rely on maintaining the content related to the main-task label.
Dependency-aware Attention Control for Unconstrained Face Recognition with Image Sets
This paper targets the problem of image set-based face verification and identification.
Permutation-invariant Feature Restructuring for Correlation-aware Image Set-based Recognition
We consider the problem of comparing the similarity of image sets with variable-quantity, quality and un-ordered heterogeneous images.
Attention Control with Metric Learning Alignment for Image Set-based Recognition
The importance of each image is usually considered either equal or based on a quality assessment of that image independent of other images and/or videos in that image set.
Conservative Wasserstein Training for Pose Estimation
We propose to incorporate inter-class correlations in a Wasserstein training framework by pre-defining ($i. e.,$ using arc length of a circle) or adaptively learning the ground metric.
Unimodal-uniform Constrained Wasserstein Training for Medical Diagnosis
In this paper, we target on this task from the perspective of loss function.
Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models
We test the verifier network on out-of-distribution detection and adversarial example detection problems, as well as anomaly detection problems in structured prediction tasks such as image caption generation.
Towards Disentangled Representations for Human Retargeting by Multi-view Learning
We study the problem of learning disentangled representations for data across multiple domains and its applications in human retargeting.
TPPO: A Novel Trajectory Predictor with Pseudo Oracle
A latent variable predictor is proposed to estimate latent variable distributions from observed and ground-truth trajectories.
Severity-Aware Semantic Segmentation With Reinforced Wasserstein Training
In addition, our method can adaptively learn the ground metric in a high-fidelity simulator, following a reinforcement alternative optimization scheme.
Disentanglement for Discriminative Visual Recognition
This chapter systematically summarize the detrimental factors as task-relevant/irrelevant semantic variations and unspecified latent variation.
AUTO3D: Novel view synthesis through unsupervisely learned variational viewpoint and global 3D representation
This paper targets on learning-based novel view synthesis from a single or limited 2D images without the pose supervision.
Reinforced Wasserstein Training for Severity-Aware Semantic Segmentation in Autonomous Driving
The ground metric of Wasserstein distance can be pre-defined following the experience on a specific task.
Mutual Information Regularized Identity-aware Facial ExpressionRecognition in Compressed Video
In the up to two orders of magnitude compressed domain, we can explicitly infer the expression from the residual frames and possibly extract identity factors from the I frame with a pre-trained face recognition network.
Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training
However, the cross entropy loss can not take the different importance of each class in an self-driving system into account.
Subtype-aware Unsupervised Domain Adaptation for Medical Diagnosis
Recent advances in unsupervised domain adaptation (UDA) show that transferable prototypical learning presents a powerful means for class conditional alignment, which encourages the closeness of cross-domain class centroids.
Identity-aware Facial Expression Recognition in Compressed Video
In the up to two orders of magnitude compressed domain, we can explicitly infer the expression from the residual frames and possible to extract identity factors from the I frame with a pre-trained face recognition network.
Energy-constrained Self-training for Unsupervised Domain Adaptation
Unsupervised domain adaptation (UDA) aims to transfer the knowledge on a labeled source domain distribution to perform well on an unlabeled target domain.
VoxelHop: Successive Subspace Learning for ALS Disease Classification Using Structural MRI
Deep learning has great potential for accurate detection and classification of diseases with medical imaging data, but the performance is often limited by the number of training datasets and memory requirements.
A Unified Conditional Disentanglement Framework for Multimodal Brain MR Image Translation
Our framework hinges on a cycle-constrained conditional adversarial training approach, where it can extract a modality-invariant anatomical feature with a modality-agnostic encoder and generate a target modality with a conditioned decoder.
Dual-cycle Constrained Bijective VAE-GAN For Tagged-to-Cine Magnetic Resonance Image Synthesis
Tagged magnetic resonance imaging (MRI) is a widely used imaging technique for measuring tissue deformation in moving organs.
Symmetric-Constrained Irregular Structure Inpainting for Brain MRI Registration with Tumor Pathology
Deformable registration of magnetic resonance images between patients with brain tumors and healthy subjects has been an important tool to specify tumor geometry through location alignment and facilitate pathological analysis.
Language model fusion for streaming end to end speech recognition
Streaming processing of speech audio is required for many contemporary practical speech recognition tasks.
Embedding Semantic Hierarchy in Discrete Optimal Transport for Risk Minimization
The ground distance matrix can be pre-defined following a priori of hierarchical semantic risk.
AI Enlightens Wireless Communication: Analyses, Solutions and Opportunities on CSI Feedback
In this paper, we give a systematic description of the 1st Wireless Communication Artificial Intelligence (AI) Competition (WAIC) which is hosted by IMT-2020(5G) Promotion Group 5G+AI Work Group.
Adapting Off-the-Shelf Source Segmenter for Target Medical Image Segmentation
To alleviate this, in this work, we target source free UDA for segmentation, and propose to adapt an ``off-the-shelf" segmentation model pre-trained in the source domain to the target domain, with an adaptive batch-wise normalization statistics adaptation framework.
Generative Self-training for Cross-domain Unsupervised Tagged-to-Cine MRI Synthesis
Self-training based unsupervised domain adaptation (UDA) has shown great potential to address the problem of domain shift, when applying a trained deep learning model in a source domain to unlabeled target domains.
Interpreting Depression From Question-wise Long-term Video Recording of SDS Evaluation
To automatically interpret depression from the SDS evaluation and the paired video, we propose an end-to-end hierarchical framework for the long-term variable-length video, which is also conditioned on the questionnaire results and the answering time.
Sparse Personalized Federated Learning
By incorporating an approximated L1-norm and the correlation between client models and global model into standard FL loss function, the performance on statistical diversity data is improved and the communicational and computational loads required in the network are reduced compared with non-sparse FL.
Structured Directional Pruning via Perturbation Orthogonal Projection
Structured pruning is an effective compression technique to reduce the computation of neural networks, which is usually achieved by adding perturbations to reduce network parameters at the cost of slightly increasing training loss.
Segmentation of Cardiac Structures via Successive Subspace Learning with Saab Transform from Cine MRI
Assessment of cardiovascular disease (CVD) with cine magnetic resonance imaging (MRI) has been used to non-invasively evaluate detailed cardiac structure and function.
Deep 3D-CNN for Depression Diagnosis with Facial Video Recording of Self-Rating Depression Scale Questionnaire
The superior performance of our system shows the validity of combining facial video recording with the SDS score for more accurate self-diagnose.
Domain Generalization under Conditional and Label Shifts via Variational Bayesian Inference
In this work, we propose a domain generalization (DG) approach to learn on several labeled source domains and transfer knowledge to a target domain that is inaccessible in training.
Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate
In this work, we propose an adversarial unsupervised domain adaptation (UDA) approach with the inherent conditional and label shifts, in which we aim to align the distributions w. r. t.
Recursively Conditional Gaussian for Ordinal Unsupervised Domain Adaptation
The UDA for ordinal classification requires inducing non-trivial ordinal distribution prior to the latent space.
BACO: A Background Knowledge- and Content-Based Framework for Citing Sentence Generation
In this paper, we focus on the problem of citing sentence generation, which entails generating a short text to capture the salient information in a cited paper and the connection between the citing and cited paper.
Self-semantic contour adaptation for cross modality brain tumor segmentation
Unsupervised domain adaptation (UDA) between two significantly disparate domains to learn high-level semantic alignment is a crucial yet challenging task.~To this end, in this work, we propose exploiting low-level edge information to facilitate the adaptation as a precursor task, which has a small cross-domain gap, compared with semantic segmentation.~The precise contour then provides spatial information to guide the semantic adaptation.
Variational Inference for Quantifying Inter-observer Variability in Segmentation of Anatomical Structures
Then, we apply a variational autoencoder network and optimize its evidence lower bound (ELBO) to efficiently approximate the distribution of the segmentation map, given an MR image.
A Multi-modal Fusion Framework Based on Multi-task Correlation Learning for Cancer Prognosis Prediction
By integrating these heterogeneous but complementary data, many multi-modal methods are proposed to study the complex mechanisms of cancers, and most of them achieve comparable or better results from previous single-modal methods.
Structure-aware Unsupervised Tagged-to-Cine MRI Synthesis with Self Disentanglement
Specifically, we propose a novel input-output image patches self-training scheme to achieve a disentanglement of underlying anatomical structures and imaging modalities.
Sparse Federated Learning with Hierarchical Personalized Models
To this end, we propose a personalized FL algorithm using a hierarchical proximal mapping based on the moreau envelop, named sparse federated learning with hierarchical personalized models (sFedHP), which significantly improves the global model performance facing diverse data.
ACT: Semi-supervised Domain-adaptive Medical Image Segmentation with Asymmetric Co-training
Unsupervised domain adaptation (UDA) has been vastly explored to alleviate domain shifts between source and target domains, by applying a well-performed model in an unlabeled target domain via supervision of a labeled source domain.
Tagged-MRI Sequence to Audio Synthesis via Self Residual Attention Guided Heterogeneous Translator
Understanding the underlying relationship between tongue and oropharyngeal muscle deformation seen in tagged-MRI and intelligible speech plays an important role in advancing speech motor control theories and treatment of speech related-disorders.
AI Enlightens Wireless Communication: A Transformer Backbone for CSI Feedback
This paper is based on the background of the 2nd Wireless Communication Artificial Intelligence (AI) Competition (WAIC) which is hosted by IMT-2020(5G) Promotion Group 5G+AIWork Group, where the framework of the eigenvector-based channel state information (CSI) feedback problem is firstly provided.
Unsupervised Domain Adaptation for Segmentation with Black-box Source Model
Unsupervised domain adaptation (UDA) has been widely used to transfer knowledge from a labeled source domain to an unlabeled target domain to counter the difficulty of labeling in a new domain.
Subtype-Aware Dynamic Unsupervised Domain Adaptation
In TPN, while the closeness of class centers between source and target domains is explicitly enforced in a latent space, the underlying fine-grained subtype structure and the cross-domain within-class compactness have not been fully investigated.
Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives
Unsupervised domain adaptation (UDA) is proposed to counter this, by leveraging both labeled source domain data and unlabeled target domain data to carry out various tasks in the target domain.
Constraining Pseudo-label in Self-training Unsupervised Domain Adaptation with Energy-based Model
Deep learning is usually data starved, and the unsupervised domain adaptation (UDA) is developed to introduce the knowledge in the labeled source domain to the unlabeled target domain.
Tensor Decomposition based Personalized Federated Learning
Federated learning (FL) is a new distributed machine learning framework that can achieve reliably collaborative training without collecting users' private data.
Memory Consistent Unsupervised Off-the-Shelf Model Adaptation for Source-Relaxed Medical Image Segmentation
Unsupervised domain adaptation (UDA) has been a vital protocol for migrating information learned from a labeled source domain to facilitate the implementation in an unlabeled heterogeneous target domain.
Differentiable modeling to unify machine learning and physical models and advance Geosciences
Here we present differentiable geoscientific modeling as a powerful pathway toward dissolving the perceived barrier between them and ushering in a paradigm shift.
Successive Subspace Learning for Cardiac Disease Classification with Two-phase Deformation Fields from Cine MRI
Cardiac cine magnetic resonance imaging (MRI) has been used to characterize cardiovascular diseases (CVD), often providing a noninvasive phenotyping tool.~While recently flourished deep learning based approaches using cine MRI yield accurate characterization results, the performance is often degraded by small training samples.
Synthesizing audio from tongue motion during speech using tagged MRI via transformer
However, elucidating the relationship between these two sources of information is challenging, due in part to the disparity in data structure between spatiotemporal motion fields (i. e., 4D motion fields) and one-dimensional audio waveforms.
Posterior Estimation Using Deep Learning: A Simulation Study of Compartmental Modeling in Dynamic PET
Purpose: This work aims at using deep learning to efficiently estimate posterior distributions of imaging parameters, which in turn can be used to derive the most probable parameters as well as their uncertainties.
NAI$_2$: Learning Noise-Aware Illuminance-Interpolator for Unsupervised Low-Light Image Enhancement
Low-light situations severely restrict the pursuit of aesthetic quality in consumer photography.
Attentive Continuous Generative Self-training for Unsupervised Domain Adaptive Medical Image Translation
We evaluated our framework on two cross-scanner/center, inter-subject translation tasks, including tagged-to-cine magnetic resonance (MR) image translation and T1-weighted MR-to-fractional anisotropy translation.
Motion-Scenario Decoupling for Rat-Aware Video Position Prediction: Strategy and Benchmark
Recently significant progress has been made in human action recognition and behavior prediction using deep learning techniques, leading to improved vision-based semantic understanding.
Incremental Learning for Heterogeneous Structure Segmentation in Brain Tumor MRI
Deep learning (DL) models for segmenting various anatomical structures have achieved great success via a static DL model that is trained in a single source domain.
MRecGen: Multimodal Appropriate Reaction Generator
Verbal and non-verbal human reaction generation is a challenging task, as different reactions could be appropriate for responding to the same behaviour.
Bias and Fairness in Chatbots: An Overview
Thus, a comprehensive overview on bias and fairness in chatbot systems is given in this paper.
Speech Audio Synthesis from Tagged MRI and Non-Negative Matrix Factorization via Plastic Transformer
The tongue's intricate 3D structure, comprising localized functional units, plays a crucial role in the production of speech.
Semi-Supervised End-To-End Contrastive Learning For Time Series Classification
The unsupervised, supervised contrastive losses and classification loss are jointly used to optimize the encoder and classifier.
Posterior Estimation for Dynamic PET imaging using Conditional Variational Inference
Specifically, we counteract the information loss in the forward process by introducing latent variables.
Vicinal Feature Statistics Augmentation for Federated 3D Medical Volume Segmentation
However, the performance of FL can be constrained by the limited availability of labeled data in small institutes and the heterogeneous (i. e., non-i. i. d.)
Automated interpretation of congenital heart disease from multi-view echocardiograms
Our video-based model can diagnose with an accuracy of 93. 9\% (binary classification), and 92. 1\% (3-class classification) in a collected 2D video testing set, which does not need key-frame selection and view annotation in testing.
Learn From Orientation Prior for Radiograph Super-Resolution: Orientation Operator Transformer
Conclusions: In this study, we propose a novel framework called $O^{2}$former for radiological image super-resolution tasks, which improves the reconstruction model's performance by introducing an orientation operator and multi-scale feature fusion strategy.
Disentangled Multimodal Brain MR Image Translation via Transformer-based Modality Infuser
Multimodal Magnetic Resonance (MR) Imaging plays a crucial role in disease diagnosis due to its ability to provide complementary information by analyzing a relationship between multimodal images on the same subject.
Treatment-wise Glioblastoma Survival Inference with Multi-parametric Preoperative MRI
In this work, we aim to predict the survival time (ST) of glioblastoma (GBM) patients undergoing different treatments based on preoperative magnetic resonance (MR) scans.
Speech motion anomaly detection via cross-modal translation of 4D motion fields from tagged MRI
In this work, we aim to develop a framework for detecting speech motion anomalies in conjunction with their corresponding speech acoustics.
Progressive Contrastive Learning with Multi-Prototype for Unsupervised Visible-Infrared Person Re-identification
To address the problem, we propose a Progressive Contrastive Learning with Multi-Prototype (PCLMP) method for USVI-ReID.
