Search Results for author:
Found 184 papers, 67 papers with code
Automatic 3D Cardiovascular MR Segmentation with Densely-Connected Volumetric ConvNets
Second, it avoids learning redundant feature maps by encouraging feature reuse and hence requires fewer parameters to achieve high performance, which is essential for medical applications with limited training data.
Label Leakage and Protection in Two-party Split Learning
Two-party split learning is a popular technique for learning a model across feature-partitioned data.
DPAUC: Differentially Private AUC Computation in Federated Learning
Federated learning (FL) has gained significant attention recently as a privacy-enhancing tool to jointly train a machine learning model by multiple participants.
Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm
In this work, we study the 1-bit convolutional neural networks (CNNs), of which both the weights and activations are binary.
LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching
The recent advancements in text-to-3D generation mark a significant milestone in generative models, unlocking new possibilities for creating imaginative 3D assets across various real-world scenarios.
Iterative Geometry Encoding Volume for Stereo Matching
The proposed IGEV-Stereo builds a combined geometry encoding volume that encodes geometry and context information as well as local matching details, and iteratively indexes it to update the disparity map.
Attention Concatenation Volume for Accurate and Efficient Stereo Matching
Stereo matching is a fundamental building block for many vision and robotics applications.
Ranked #1 on
Stereo Depth Estimation
on Spring
Accurate and Efficient Stereo Matching via Attention Concatenation Volume
In this paper, we present a novel cost volume construction method, named attention concatenation volume (ACV), which generates attention weights from correlation clues to suppress redundant information and enhance matching-related information in the concatenation volume.
MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning
In this paper, we propose a novel meta learning approach for automatic channel pruning of very deep neural networks.
CGI-Stereo: Accurate and Real-Time Stereo Matching via Context and Geometry Interaction
In this paper, we propose CGI-Stereo, a novel neural network architecture that can concurrently achieve real-time performance, competitive accuracy, and strong generalization ability.
Understanding the Tricks of Deep Learning in Medical Image Segmentation: Challenges and Future Directions
Over the past few years, the rapid development of deep learning technologies for computer vision has significantly improved the performance of medical image segmentation (MedISeg).
Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics
AI-synthesized face-swapping videos, commonly known as DeepFakes, is an emerging problem threatening the trustworthiness of online information.
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset
Second, to better cover the stochastic distribution of real rain streaks, we propose a novel SPatial Attentive Network (SPANet) to remove rain streaks in a local-to-global manner.
Ranked #3 on
Single Image Deraining
on RainCityscapes
Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance
To address the training difficulty, we propose a training algorithm using a tighter approximation to the derivative of the sign function, a magnitude-aware gradient for weight updating, a better initialization method, and a two-step scheme for training a deep network.
SR-LIVO: LiDAR-Inertial-Visual Odometry and Mapping with Sweep Reconstruction
Existing LiDAR-inertial-visual odometry and mapping (LIV-SLAM) systems mainly utilize the LiDAR-inertial odometry (LIO) module for structure reconstruction and the visual-inertial odometry (VIO) module for color rendering.
Boundary and Entropy-driven Adversarial Learning for Fundus Image Segmentation
The cross-domain discrepancy (domain shift) hinders the generalization of deep neural networks to work on different domain datasets. In this work, we present an unsupervised domain adaptation framework, called Boundary and Entropy-driven Adversarial Learning (BEAL), to improve the OD and OC segmentation performance, especially on the ambiguous boundary regions.
SAMUS: Adapting Segment Anything Model for Clinically-Friendly and Generalizable Ultrasound Image Segmentation
Segment anything model (SAM), an eminent universal image segmentation model, has recently gathered considerable attention within the domain of medical image segmentation.
Generalizable Cross-modality Medical Image Segmentation via Style Augmentation and Dual Normalization
For medical image segmentation, imagine if a model was only trained using MR images in source domain, how about its performance to directly segment CT images in target domain?
Segment Anything Model for Medical Images?
To fully validate SAM's performance on medical data, we collected and sorted 53 open-source datasets and built a large medical segmentation dataset with 18 modalities, 84 objects, 125 object-modality paired targets, 1050K 2D images, and 6033K masks.
Tripartite Information Mining and Integration for Image Matting
Regarding the nature of image matting, most researches have focused on solutions for transition regions.
Deep Attentive Features for Prostate Segmentation in 3D Transrectal Ultrasound
Our attention module utilizes the attention mechanism to selectively leverage the multilevel features integrated from different layers to refine the features at each individual layer, suppressing the non-prostate noise at shallow layers of the CNN and increasing more prostate details into features at deep layers.
Real-time 6K Image Rescaling with Rate-distortion Optimization
Then, an efficient frequency-aware decoder reconstructs a high-fidelity HR image from the LR one in real time.
Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving
In this work, we propose a new robustness benchmark to evaluate the depth estimation system under various noisy pose settings.
Ranked #1 on
Monocular Depth Estimation
on DDAD
Unleashing the Strengths of Unlabeled Data in Pan-cancer Abdominal Organ Quantification: the FLARE22 Challenge
The best-performing algorithms successfully generalized to holdout external validation sets, achieving a median DSC of 89. 5\%, 90. 9\%, and 88. 3\% on North American, European, and Asian cohorts, respectively.
Where Is My Mirror?
To the best of our knowledge, this is the first work to address the mirror segmentation problem with a computational approach.
Exposing Deep Fakes Using Inconsistent Head Poses
In this paper, we propose a new method to expose AI-generated fake face images or videos (commonly known as the Deep Fakes).
Real-time Streaming Video Denoising with Bidirectional Buffers
Recent multi-output inference works propagate the bidirectional temporal feature with a parallel or recurrent framework, which either suffers from performance drops on the temporal edges of clips or can not achieve online inference.
Ranked #1 on
Video Denoising
on CRVD
Camouflaged Object Segmentation with Distraction Mining
In this paper, we strive to embrace challenges towards effective and efficient COS. To this end, we develop a bio-inspired framework, termed Positioning and Focus Network (PFNet), which mimics the process of predation in nature.
Ranked #11 on
Dichotomous Image Segmentation
on DIS-TE3
Camouflaged Object Segmentation
Dichotomous Image Segmentation
+3
Dual-Distribution Discrepancy for Anomaly Detection in Chest X-Rays
Subsequently, inter-discrepancy between the two modules, and intra-discrepancy inside the module that is trained on only normal images are designed as anomaly scores to indicate anomalies.
Object Tracking by Jointly Exploiting Frame and Event Domain
Our approach's effectiveness is enforced by a novel designed cross-domain attention schemes, which can effectively enhance features based on self- and cross-domain attention schemes; The adaptiveness is guarded by a specially designed weighting scheme, which can adaptively balance the contribution of the two domains.
Ranked #3 on
Object Tracking
on FE108
Dual-distribution discrepancy with self-supervised refinement for anomaly detection in medical images
Due to the high-cost annotations of abnormal images, most methods utilize only known normal images during training and identify samples deviating from the normal profile as anomalies in the testing phase.
Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching
Stereo matching methods based on iterative optimization, like RAFT-Stereo and IGEV-Stereo, have evolved into a cornerstone in the field of stereo matching.
Instructive Feature Enhancement for Dichotomous Medical Image Segmentation
Deep neural networks have been widely applied in dichotomous medical image segmentation (DMIS) of many anatomical structures in several modalities, achieving promising performance.
FreeCOS: Self-Supervised Learning from Fractals and Unlabeled Images for Curvilinear Object Segmentation
Curvilinear object segmentation is critical for many applications.
CPT: Efficient Deep Neural Network Training via Cyclic Precision
In this paper, we attempt to explore low-precision training from a new perspective as inspired by recent findings in understanding DNN training: we conjecture that DNNs' precision might have a similar effect as the learning rate during DNN training, and advocate dynamic precision along the training trajectory for further boosting the time/energy efficiency of DNN training.
Affinity Feature Strengthening for Accurate, Complete and Robust Vessel Segmentation
Vessel segmentation is crucial in many medical image applications, such as detecting coronary stenoses, retinal vessel diseases and brain aneurysms.
A Two-Stage Attentive Network for Single Image Super-Resolution
Recently, deep convolutional neural networks (CNNs) have been widely explored in single image super-resolution (SISR) and contribute remarkable progress.
Out-of-domain GAN inversion via Invertibility Decomposition for Photo-Realistic Human Face Manipulation
In this paper, we propose a novel framework that enhances the fidelity of human face inversion by designing a new module to decompose the input images to ID and OOD partitions with invertibility masks.
MC-Stereo: Multi-peak Lookup and Cascade Search Range for Stereo Matching
This architecture mitigates the multi-peak distribution problem in matching through the multi-peak lookup strategy, and integrates the coarse-to-fine concept into the iterative framework via the cascade search range.
Co-trained convolutional neural networks for automated detection of prostate cancer in multi-parametric MRI
Each network is trained using images of a single modality in a weakly-supervised manner by providing a set of prostate images with image-level labels indicating only the presence of PCa without priors of lesions’ locations.
A Discrepancy Aware Framework for Robust Anomaly Detection
To alleviate this issue, we present a Discrepancy Aware Framework (DAF), which demonstrates robust performance consistently with simple and cheap strategies across different anomaly detection benchmarks.
A Deep Attentive Convolutional Neural Network for Automatic Cortical Plate Segmentation in Fetal MRI
Automatic segmentation of the cortical plate, on the other hand, is challenged by the relatively low resolution of the reconstructed fetal brain MRI scans compared to the thin structure of the cortical plate, partial voluming, and the wide range of variations in the morphology of the cortical plate as the brain matures during gestation.
Agent with Warm Start and Active Termination for Plane Localization in 3D Ultrasound
In this study, we propose a novel reinforcement learning (RL) framework to automatically localize fetal brain standard planes in 3D US.
Adaptive Densely Connected Super-Resolution Reconstruction
For a better performance in single image super-resolution(SISR), we present an image super-resolution algorithm based on adaptive dense connection (ADCSR).
Agent with Warm Start and Adaptive Dynamic Termination for Plane Localization in 3D Ultrasound
2D US has to perform scanning for each SP, which is time-consuming and operator-dependent.
AWSnet: An Auto-weighted Supervision Attention Network for Myocardial Scar and Edema Segmentation in Multi-sequence Cardiac Magnetic Resonance Images
Extensive experimental results on a publicly available dataset from Myocardial pathology segmentation combining multi-sequence CMR (MyoPS 2020) demonstrate our method can achieve promising performance compared with other state-of-the-art methods.
FedMix: Mixed Supervised Federated Learning for Medical Image Segmentation
To relax this assumption, in this work, we propose a label-agnostic unified federated learning framework, named FedMix, for medical image segmentation based on mixed image labels.
Object Detection in Foggy Scenes by Embedding Depth and Reconstruction into Domain Adaptation
In our DA framework, we retain the depth and background information during the domain feature alignment.
A Global Benchmark of Algorithms for Segmenting Late Gadolinium-Enhanced Cardiac Magnetic Resonance Imaging
Segmentation of cardiac images, particularly late gadolinium-enhanced magnetic resonance imaging (LGE-MRI) widely used for visualizing diseased cardiac structures, is a crucial first step for clinical diagnosis and treatment.
GSMorph: Gradient Surgery for cine-MRI Cardiac Deformable Registration
In this study, we construct a registration model based on the gradient surgery mechanism, named GSMorph, to achieve a hyperparameter-free balance on multiple losses.
In the Blink of an Eye: Event-based Emotion Recognition
To the best of our knowledge, our method is the first eye-based emotion recognition method that leverages event-based cameras and spiking neural network.
FSOINet: Feature-Space Optimization-Inspired Network for Image Compressive Sensing
In recent years, deep learning-based image compressive sensing (ICS) methods have achieved brilliant success.
FedIIC: Towards Robust Federated Learning for Class-Imbalanced Medical Image Classification
In this paper, we present a privacy-preserving FL method named FedIIC to combat class imbalance from two perspectives: feature learning and classifier learning.
Bi-directional Object-context Prioritization Learning for Saliency Ranking
We observe that spatial attention works concurrently with object-based attention in the human visual recognition system.
Bidirectional Semi-supervised Dual-branch CNN for Robust 3D Reconstruction of Stereo Endoscopic Images via Adaptive Cross and Parallel Supervisions
The learned knowledge flows across branches along two directions: a cross direction (disparity guides distribution in ACS) and a parallel direction (disparity guides disparity in APS).
DoFE: Domain-oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets
Our DoFE framework dynamically enriches the image features with additional domain prior knowledge learned from multi-source domains to make the semantic features more discriminative.
Deep Polarization Reconstruction With PDAVIS Events
The polarization event camera PDAVIS is a novel bio-inspired neuromorphic vision sensor that reports both conventional polarization frames and asynchronous, continuously per-pixel polarization brightness changes (polarization events) with fast temporal resolution and large dynamic range.
Total Least Squares Regression in Input Sparsity Time
In the total least squares problem, one is given an $m \times n$ matrix $A$, and an $m \times d$ matrix $B$, and one seeks to "correct" both $A$ and $B$, obtaining matrices $\hat{A}$ and $\hat{B}$, so that there exists an $X$ satisfying the equation $\hat{A}X = \hat{B}$.
Dual-view Correlation Hybrid Attention Network for Robust Holistic Mammogram Classification
Mammogram image is important for breast cancer screening, and typically obtained in a dual-view form, i. e., cranio-caudal (CC) and mediolateral oblique (MLO), to provide complementary information.
Deriving Autism Spectrum Disorder Functional Networks from RS-FMRI Data using Group ICA and Dictionary Learning
Fourth, we generate three corresponding masks based on the 20 selected ROIs from group ICA, the 20 ROIs selected from dictionary learning, and the 40 combined ROIs selected from both.
A Foundation Model for General Moving Object Segmentation in Medical Images
In this paper, we propose the first foundation model, named iMOS, for MOS in medical images.
Exploiting Polarized Material Cues for Robust Car Detection
Car detection is an important task that serves as a crucial prerequisite for many automated driving functions.
Inflated 3D Convolution-Transformer for Weakly-supervised Carotid Stenosis Grading with Ultrasound Videos
First, to avoid the requirement of laborious and unreliable annotation, we propose a novel and effective video classification network for weakly-supervised CSG.
Hybrid Attention for Automatic Segmentation of Whole Fetal Head in Prenatal Ultrasound Volumes
In this paper, we propose the first fully-automated solution to segment the whole fetal head in US volumes.
Deep graph matching meets mixed-integer linear programming: Relax at your own risk ?
Graph matching is an important problem that has received widespread attention, especially in the field of computer vision.
Active Object Reconstruction Using a Guided View Planner
Inspired by the recent advance of image-based object reconstruction using deep learning, we present an active reconstruction model using a guided view planner.
Neural Compatibility Modeling with Attentive Knowledge Distillation
Nevertheless, existing studies overlook the rich valuable knowledge (rules) accumulated in fashion domain, especially the rules regarding clothing matching.
Image Correction via Deep Reciprocating HDR Transformation
Given an input LDR image, we first reconstruct the missing details in the HDR domain.
Time-Space Tradeoffs for Learning from Small Test Spaces: Learning Low Degree Polynomial Functions
We develop an extension of recently developed methods for obtaining time-space tradeoff lower bounds for problems of learning from random test samples to handle the situation where the space of tests is signficantly smaller than the space of inputs, a class of learning problems that is not handled by prior work.
Fine-grained Recurrent Neural Networks for Automatic Prostate Segmentation in Ultrasound Images
Additionally, our approach is general and can be extended to other medical image segmentation tasks, where boundary incompleteness is one of the main challenges.
Concept based Attention
Attention endows animals an ability to concentrate on the most relevant information among a deluge of distractors at any given time, either through volitionally 'top-down' biasing, or driven by automatically 'bottom-up' saliency of stimuli, in favour of advantageous competition in neural modulations for information processing.
Tool Breakage Detection using Deep Learning
In this work, we use the spindle current approach to detect the breakage of machine tools, which has the high performance of real-time monitoring, low cost, and easy to install.
Deep Hierarchical Machine: a Flexible Divide-and-Conquer Architecture
We propose Deep Hierarchical Machine (DHM), a model inspired from the divide-and-conquer strategy while emphasizing representation learning ability and flexibility.
Combating Uncertainty with Novel Losses for Automatic Left Atrium Segmentation
In this paper, we propose a fully-automated framework to segment left atrium in gadolinium-enhanced MR volumes.
Pyramid Network with Online Hard Example Mining for Accurate Left Atrium Segmentation
Accurately segmenting left atrium in MR volume can benefit the ablation procedure of atrial fibrillation.
Semi-supervised mp-MRI Data Synthesis with StitchLayer and Auxiliary Distance Maximization
Experimental results show that our method can effectively synthesize a large variety of mpMRI images which contain meaningful CS PCa lesions, display a good visual quality and have the correct paired relationship.
Synthesizing Multi-Parameter Magnetic Resonance Imaging (Mp-Mri) Data
Active Matting
Our aim is to discover the most informative sequence of regions for user input in order to produce a good alpha matte with minimum labeling efforts.
Patch-based Output Space Adversarial Learning for Joint Optic Disc and Cup Segmentation
In this paper, we present a novel patchbased Output Space Adversarial Learning framework (pOSAL) to jointly and robustly segment the OD and OC from different fundus image datasets.
Ranked #2 on
Optic Disc Segmentation
on REFUGE
Evaluation of Algorithms for Multi-Modality Whole Heart Segmentation: An Open-Access Grand Challenge
This manuscript presents the methodologies and evaluation results for the WHS algorithms selected from the submissions to the Multi-Modality Whole Heart Segmentation (MM-WHS) challenge, in conjunction with MICCAI 2017.
Deep Reinforcement Learning of Volume-guided Progressive View Inpainting for 3D Point Scene Completion from a Single Depth Image
Given a single depth image, our method first goes through the 3D volume branch to obtain a volumetric scene reconstruction as a guide to the next view inpainting step, which attempts to make up the missing information; the third step involves projecting the volume under the same view of the input, concatenating them to complete the current view depth, and integrating all depth into the point cloud.
Exposing GAN-synthesized Faces Using Landmark Locations
Generative adversary networks (GANs) have recently led to highly realistic image synthesis results.
Quadratic Suffices for Over-parametrization via Matrix Chernoff Bound
We improve the over-parametrization size over two beautiful results [Li and Liang' 2018] and [Du, Zhai, Poczos and Singh' 2019] in deep learning theory.
Hiding Faces in Plain Sight: Disrupting AI Face Synthesis with Adversarial Perturbations
Recent years have seen fast development in synthesizing realistic human faces using AI technologies.
Uncertainty-Guided Domain Alignment for Layer Segmentation in OCT Images
Automatic and accurate segmentation for retinal and choroidal layers of Optical Coherence Tomography (OCT) is crucial for detection of various ocular diseases.
DRFN: Deep Recurrent Fusion Network for Single-Image Super-Resolution with Large Factors
Recently, single-image super-resolution has made great progress owing to the development of deep convolutional neural networks (CNNs).
Urban flows prediction from spatial-temporal data using machine learning: A survey
Urban spatial-temporal flows prediction is of great importance to traffic management, land use, public safety, etc.
Joint Segmentation and Landmark Localization of Fetal Femur in Ultrasound Volumes
In this paper, we propose an effective framework for simultaneous segmentation and landmark localization in prenatal ultrasound volumes.
FetusMap: Fetal Pose Estimation in 3D Ultrasound
(i) This is the first work about 3D pose estimation of fetus in the literature.
One-Shot Imitation Filming of Human Motion Videos
Imitation learning has been applied to mimic the operation of a human cameraman in several autonomous cinematography systems.
Remove Appearance Shift for Ultrasound Image Segmentation via Fast and Universal Style Transfer
In this paper, we propose a novel and intuitive framework to remove the appearance shift, and hence improve the generalization ability of DNNs.
Sketching Transformed Matrices with Applications to Natural Language Processing
We show that our approach obtains small error and is efficient in both space and time.
Synthesis and Edition of Ultrasound Images via Sketch Guided Progressive Growing GANs
Efficiently synthesizing realistic, editable and high resolution US images can solve the problems.
Region Proposal Network with Graph Prior and IoU-Balance Loss for Landmark Detection in 3D Ultrasound
The performance of the proposed framework is evaluated on a 3D US dataset to detect five key fetal facial landmarks.
TENet: Triple Excitation Network for Video Salient Object Detection
In this paper, we propose a simple yet effective approach, named Triple Excitation Network, to reinforce the training of video salient object detection (VSOD) from three aspects, spatial, temporal, and online excitations.
Searching Collaborative Agents for Multi-plane Localization in 3D Ultrasound
In this study, we propose a novel Multi-Agent Reinforcement Learning (MARL) framework to localize multiple uterine SPs in 3D US simultaneously.
Multi-agent Reinforcement Learning
Neural Architecture Search
Computer-aided Tumor Diagnosis in Automated Breast Ultrasound using 3D Detection Network
The efficacy of our network is verified from a collected dataset of 418 patients with 145 benign tumors and 273 malignant tumors.
Designing Neural Networks for Real-Time Systems
This issue stems largely from the implementation strategies used within common neural network frameworks -- their underlying source code is often simply unsuitable for formal techniques such as static timing analysis.
Style-invariant Cardiac Image Segmentation with Test-time Augmentation
Based on the zero-shot style transfer to remove appearance shift and test-time augmentation to explore diverse underlying anatomy, our proposed method is effective in combating the appearance shift.
Weakly-supervised Salient Instance Detection
Inspired by this insight, we propose to use class and subitizing labels as weak supervision for the SID problem.
Contrastive Rendering for Ultrasound Image Segmentation
However, the lack of sharp boundaries in US images still remains an inherent challenge for segmentation.
Multi-scale Information Assembly for Image Matting
Image matting is a long-standing problem in computer graphics and vision, mostly identified as the accurate estimation of the foreground in input images.
Generalize Ultrasound Image Segmentation via Instant and Plug & Play Style Transfer
Deep segmentation models that generalize to images with unknown appearance are important for real-world medical image analysis.
Automatic Comic Generation with Stylistic Multi-page Layouts and Emotion-driven Text Balloon Generation
Finally, as opposed to using the same type of balloon as in previous works, we propose an emotion-aware balloon generation method to create different types of word balloons by analyzing the emotion of subtitles and audios.
Smart Scribbles for Image Mating
Image matting is an ill-posed problem that usually requires additional user input, such as trimaps or scribbles.
FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Convergence Analysis
Nevertheless, training analysis of neural networks in FL is non-trivial for two reasons: first, the objective loss function we are optimizing is non-smooth and non-convex, and second, we are even not updating in the gradient direction.
Learn Fine-grained Adaptive Loss for Multiple Anatomical Landmark Detection in Medical Images
Our proposed framework is general and shows the potential to improve the efficiency of anatomical landmark detection.
Searching Collaborative Agents for Multi-plane Localization in 3D Ultrasound
First, our proposed method is general and it can accurately localize multiple SPs in different challenging US datasets.
Multi-agent Reinforcement Learning
Neural Architecture Search
Vertical Federated Learning without Revealing Intersection Membership
In this paper, we propose a vFL framework based on Private Set Union (PSU) that allows each party to keep sensitive membership information to itself.
Joint Landmark and Structure Learning for Automatic Evaluation of Developmental Dysplasia of the Hip
In this study, we propose a multi-task framework to learn the relationships among landmarks and structures jointly and automatically evaluate DDH.
LENAS: Learning-based Neural Architecture Search and Ensemble for 3D Radiotherapy Dose Prediction
To the best of our knowledge, this is the first attempt to investigate NAS and knowledge distillation in ensemble learning, especially in the field of medical image analysis.
Prior-Induced Information Alignment for Image Matting
Image matting is an ill-posed problem that aims to estimate the opacity of foreground pixels in an image.
Depth-Aware Mirror Segmentation
To exploit depth information in mirror segmentation, we first construct a large-scale RGB-D mirror segmentation dataset, which we subsequently employ to train a novel depth-aware mirror segmentation framework.
Feature-Level Collaboration: Joint Unsupervised Learning of Optical Flow, Stereo Depth and Camera Motion
In this paper, we show that effective feature-level collaboration of the networks for the three respective tasks could achieve much greater performance improvement for all three tasks than only loss-level joint optimization.
Flip Learning: Erase to Segment
Weakly-supervised segmentation (WSS) can help reduce time-consuming and cumbersome manual annotation.
Style Curriculum Learning for Robust Medical Image Segmentation
A style transfer model with style fusion is employed to generate the curriculum samples.
Self Context and Shape Prior for Sensorless Freehand 3D Ultrasound Reconstruction
In this paper, we propose a novel approach to sensorless freehand 3D US reconstruction considering the complex skill sequences.
Multi-domain Collaborative Feature Representation for Robust Visual Object Tracking
Jointly exploiting multiple different yet complementary domain information has been proven to be an effective way to perform robust object tracking.
Statistical Dependency Guided Contrastive Learning for Multiple Labeling in Prenatal Ultrasound
In this study, we build a novel multi-label learning (MLL) scheme to identify multiple standard planes and corresponding anatomical structures of fetus simultaneously.
WRICNet:A Weighted Rich-scale Inception Coder Network for Multi-Resolution Remote Sensing Image Change Detection
With the purpose of improving change detection effectiveness of the model in the multi-resolution data set, a weighted rich-scale inception coder network (WRICNet) is proposed in this article, which can make a great fusion of shallow multi-scale features, and deep multi-scale features.
Self-supervised Representation Learning for Trip Recommendation
Although recent deep recursive models (e. g., RNN) are capable of alleviating these concerns, existing solutions hardly recognize the practical reality, such as the diversity of tourist demands, uncertainties in the trip generation, and the complex visiting preference.
Monocular Depth Estimation with Sharp Boundary
In order to mitigate the boundary blur problem, we focus on the above two impact factors.
Automated Pulmonary Embolism Detection from CTPA Images Using an End-to-End Convolutional Neural Network
We have evaluated our approach using the 20 CTPA test dataset from the PE challenge, achieving a sensitivity of 78. 9%, 80. 7% and 80. 7% at 2 false positives per volume at 0mm, 2mm and 5mm localization error, which is superior to the state-of-the-art methods.
Learning to Detect Instance-level Salient Objects Using Complementary Image Labels
However, it is non-trivial to use only class labels to learn instance-aware saliency information, as salient instances with high semantic affinities may not be easily separated by the labels.
CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation
Acquiring the most representative examples via active learning (AL) can benefit many data-dependent computer vision tasks by minimizing efforts of image-level or pixel-wise annotations.
SECP-Net: SE-Connection Pyramid Network of Organ At Risk Segmentation for Nasopharyngeal Carcinoma
SECP-Net extracts global and multi-size information flow with se connection (SEC) modules and a pyramid structure of network for improving the segmentation performance, especially that of small organs.
Label Leakage and Protection from Forward Embedding in Vertical Federated Learning
As the raw labels often contain highly sensitive information, some recent work has been proposed to prevent the label leakage from the backpropagated gradients effectively in vFL.
Differentially Private Label Protection in Split Learning
Split learning is a distributed training framework that allows multiple parties to jointly train a machine learning model over vertically partitioned data (partitioned by attributes).
HASA: Hybrid Architecture Search with Aggregation Strategy for Echinococcosis Classification and Ovary Segmentation in Ultrasound Images
The hybrid framework consists of a pre-trained backbone and several searched cells (i. e., network building blocks), which takes advantage of the strengths of both NAS and the expert knowledge from existing convolutional neural networks.
Sketch guided and progressive growing GAN for realistic and editable ultrasound image synthesis
Our main contributions include: 1) we present the first work that can synthesize realistic B-mode US images with high-resolution and customized texture editing features; 2) to enhance structural details of generated images, we propose to introduce auxiliary sketch guidance into a conditional GAN.
Differentially Private AUC Computation in Vertical Federated Learning
In this work, we propose two evaluation algorithms that can more accurately compute the widely used AUC (area under curve) metric when using label DP in vFL.
Spiking Transformers for Event-Based Single Object Tracking
In particular, the proposed architecture features a transformer module to provide global spatial information and a spiking neural network (SNN) module for extracting temporal cues.
Glass Segmentation Using Intensity and Spectral Polarization Cues
Transparent and semi-transparent materials pose significant challenges for existing scene understanding and segmentation algorithms due to their lack of RGB texture which impedes the extraction of meaningful features.
Ranked #14 on
Semantic Segmentation
on KITTI-360
Accurate Scoliosis Vertebral Landmark Localization on X-ray Images via Shape-constrained Multi-stage Cascaded CNNs
Vertebral landmark localization is a crucial step for variant spine-related clinical applications, which requires detecting the corner points of 17 vertebrae.
Differentially Private Multi-Party Data Release for Linear Regression
Differentially Private (DP) data release is a promising technique to disseminate data without compromising the privacy of data subjects.
Online Reflective Learning for Robust Medical Image Segmentation
Deep segmentation models often face the failure risks when the testing image presents unseen distributions.
Agent with Tangent-based Formulation and Anatomical Perception for Standard Plane Localization in 3D Ultrasound
First, we formulate SP localization in 3D US as a tangent-point-based problem in RL to restructure the action space and significantly reduce the search space.
Weakly-supervised High-fidelity Ultrasound Video Synthesis with Feature Decoupling
First, leveraging the advantages of self- and fully-supervised learning, our proposed system is trained in weakly-supervised manner for keypoint detection.
Fine-grained Correlation Loss for Regression
In this work, we propose to revisit the classic regression tasks with novel investigations on directly optimizing the fine-grained correlation losses.
Multi-Attribute Attention Network for Interpretable Diagnosis of Thyroid Nodules in Ultrasound Images
To overcome this, we propose a novel deep learning framework called multi-attribute attention network (MAA-Net) that is designed to mimic the clinical diagnosis process.
Progressive Glass Segmentation
First, we attempt to bridge the characteristic gap between different levels of features by developing a Discriminability Enhancement (DE) module which enables level-specific features to be a more discriminative representation, alleviating the features incompatibility for fusion.
Comparative study of machine learning and deep learning methods on ASD classification
The autism dataset is studied to identify the differences between autistic and healthy groups.
Blinder: End-to-end Privacy Protection in Sensing Systems via Personalized Federated Learning
This paper proposes a sensor data anonymization model that is trained on decentralized data and strikes a desirable trade-off between data utility and privacy, even in heterogeneous settings where the sensor data have different underlying distributions.
Explore Contextual Information for 3D Scene Graph Generation
3D scene graph generation (SGG) has been of high interest in computer vision.
Point Cloud Scene Completion with Joint Color and Semantic Estimation from Single RGB-D Image
Given a single RGB-D image, our method first predicts its semantic segmentation map and goes through the 3D volume branch to obtain a volumetric scene reconstruction as a guide to the next view inpainting step, which attempts to make up the missing information; the third step involves projecting the volume under the same view of the input, concatenating them to complete the current view RGB-D and segmentation map, and integrating all RGB-D and segmentation maps into the point cloud.
Wider and Higher: Intensive Integration and Global Foreground Perception for Image Matting
This paper reviews recent deep-learning-based matting research and conceives our wider and higher motivation for image matting.
Hierarchical and Progressive Image Matting
In this paper, we propose an end-to-end Hierarchical and Progressive Attention Matting Network (HAttMatting++), which can better predict the opacity of the foreground from single RGB images without additional input.
An Attention-Guided and Wavelet-Constrained Generative Adversarial Network for Infrared and Visible Image Fusion
The GAN-based infrared and visible image fusion methods have gained ever-increasing attention due to its effectiveness and superiority.
Generative Adversarial Network
Infrared And Visible Image Fusion
Label Inference Attack against Split Learning under Regression Setting
In this work, we step further to study the leakage in the scenario of the regression model, where the private labels are continuous numbers (instead of discrete labels in classification).
Netflix and Forget: Efficient and Exact Machine Unlearning from Bi-linear Recommendations
Without incurring the cost of re-training, and without degrading the model unnecessarily, we develop Unlearn-ALS by making a few key modifications to the fine-tuning procedure under Alternating Least Squares optimisation, thus applicable to any bi-linear models regardless of the training procedure.
Exploiting Implicit Rigidity Constraints via Weight-Sharing Aggregation for Scene Flow Estimation from Point Clouds
Scene flow estimation, which predicts the 3D motion of scene points from point clouds, is a core task in autonomous driving and many other 3D vision applications.
Robust Multimodal Fusion for Human Activity Recognition
Compared to 2 related robust fusion architectures, Centaur is more robust, achieving 11. 59-17. 52% higher accuracy in HAR, especially in the presence of consecutive missing data in multiple sensor channels.
Hierarchical Agent-based Reinforcement Learning Framework for Automated Quality Assessment of Fetal Ultrasound Video
Ultrasound is the primary modality to examine fetal growth during pregnancy, while the image quality could be affected by various factors.
Differentially Private Attention Computation
Inspired by [Vyas, Kakade and Barak 2023], in this work, we provide a provable result for showing how to differentially private approximate the attention matrix.
Generating high-quality 3DMPCs by adaptive data acquisition and NeREF-based radiometric calibration with UGV plant phenotyping system
The integrity of the whole-plant data was improved by an average of 23. 6% compared to the fixed viewpoints alone.
An image segmentation algorithm based on multi-scale feature pyramid network
Medical image segmentation is particularly critical as a prerequisite for relevant quantitative analysis in the treatment of clinical diseases.
Frame-Event Alignment and Fusion Network for High Frame Rate Tracking
The alignment module is responsible for cross-style and cross-frame-rate alignment between frame and event modalities under the guidance of the moving cues furnished by events.
Fourier Test-time Adaptation with Multi-level Consistency for Robust Classification
Second, we introduce a regularization technique that utilizes style interpolation consistency in the frequency space to encourage self-consistency in the logit space of the model output.
Multi-IMU with Online Self-Consistency for Freehand 3D Ultrasound Reconstruction
Ultrasound (US) imaging is a popular tool in clinical diagnosis, offering safety, repeatability, and real-time capabilities.
Fast Quantum Algorithm for Attention Computation
It is well-known that quantum machine has certain computational advantages compared to the classical machine.
The Multi-modality Cell Segmentation Challenge: Towards Universal Solutions
This benchmark and the improved algorithm offer promising avenues for more accurate and versatile cell analysis in microscopy imaging.
OnUVS: Online Feature Decoupling Framework for High-Fidelity Ultrasound Video Synthesis
Second, to better preserve the integrity and textural information of US images, we implemented a dual-decoder that decouples the content and textural features in the generator.
PE-MED: Prompt Enhancement for Interactive Medical Image Segmentation
It can prevent the highly unfavorable scenarios, such as encountering a blank mask as the initial input after the first interaction.
Bi-Modality Medical Image Synthesis Using Semi-Supervised Sequential Generative Adversarial Networks
A method for measuring the synthesis complexity is proposed to automatically determine the synthesis order in our sequential GAN.
FFPN: Fourier Feature Pyramid Network for Ultrasound Image Segmentation
In this paper, we introduce a novel Fourier-anchor-based DTS framework called Fourier Feature Pyramid Network (FFPN) to address the aforementioned issues.
Single Depth-image 3D Reflection Symmetry and Shape Prediction
In this paper, we present Iterative Symmetry Completion Network (ISCNet), a single depth-image shape completion method that exploits reflective symmetry cues to obtain more detailed shapes.
IHNet: Iterative Hierarchical Network Guided by High-Resolution Estimated Information for Scene Flow Estimation
This approach circulates high-resolution estimated information (scene flow and feature) from the preceding iteration back to the low-resolution layer of the current iteration.
Multi-view Spectral Polarization Propagation for Video Glass Segmentation
In this paper, we present the first polarization-guided video glass segmentation propagation solution (PGVS-Net) that can robustly and coherently propagate glass segmentation in RGB-P video sequences.
A Geometrical Approach to Evaluate the Adversarial Robustness of Deep Neural Networks
Hence, given different inputs, it requires different time for converging to an adversarial sample.
Distractor-aware Event-based Tracking
We demonstrate that our tracker has superior performance against the state-of-the-art trackers in terms of both accuracy and efficiency.
Debunking Free Fusion Myth: Online Multi-view Anomaly Detection with Disentangled Product-of-Experts Modeling
Multi-view or even multi-modal data is appealing yet challenging for real-world applications.
FetusMapV2: Enhanced Fetal Pose Estimation in 3D Ultrasound
However, accurately estimating the 3D fetal pose in US volume has several challenges, including poor image quality, limited GPU memory for tackling high dimensional data, symmetrical or ambiguous anatomical structures, and considerable variations in fetal poses.
Memory-Efficient Optical Flow via Radius-Distribution Orthogonal Cost Volume
The full 4D cost volume in Recurrent All-Pairs Field Transforms (RAFT) or global matching by Transformer achieves impressive performance for optical flow estimation.
Optimized Parallelization of Boundary Integral Poisson-Boltzmann Solvers
By considering the advantages of current algorithms and computer hardware, we focus on the parallelization of the treecode-accelerated boundary integral (TABI) PB solver using the Message Passing Interface (MPI) on CPUs and the direct-sum boundary integral (DSBI) PB solver using KOKKOS on GPUs.
Learning to Prompt Knowledge Transfer for Open-World Continual Learning
This paper studies the problem of continual learning in an open-world scenario, referred to as Open-world Continual Learning (OwCL).
Federated Continual Learning via Knowledge Fusion: A Survey
The key objective of FCL is to fuse heterogeneous knowledge from different clients and retain knowledge of previous tasks while learning on new ones.
FlowDA: Unsupervised Domain Adaptive Framework for Optical Flow Estimation
This paper introduces FlowDA, an unsupervised domain adaptive (UDA) framework for optical flow estimation.
Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention
They struggle to acquire new knowledge while also retaining previously learned knowledge. To address these problems, we propose a semantic segmentation method for multiple adverse weather conditions that incorporates adaptive knowledge acquisition, pseudolabel blending, and weather composition replay.
Hierarchical Continual Reinforcement Learning via Large Language Model
Despite the progress in continual reinforcement learning (CRL), existing methods often suffer from insufficient knowledge transfer, particularly when the tasks are diverse.
Thyroid ultrasound diagnosis improvement via multi-view self-supervised learning and two-stage pre-training
In this study, we proposed a multi-view contrastive self-supervised method to improve thyroid nodule classification and segmentation performance with limited manual labels.
HDRFlow: Real-Time HDR Video Reconstruction with Large Motions
HDRFlow has three novel designs: an HDR-domain alignment loss (HALoss), an efficient flow network with a multi-size large kernel (MLK), and a new HDR flow training scheme.
Open Continual Feature Selection via Granular-Ball Knowledge Transfer
To this end, the proposed CFS method combines the strengths of continual learning (CL) with granular-ball computing (GBC), which focuses on constructing a granular-ball knowledge base to detect unknown classes and facilitate the transfer of previously learned knowledge for further feature selection.
Phasic Diversity Optimization for Population-Based Reinforcement Learning
Furthermore, we construct a dogfight scenario for aerial agents to demonstrate the practicality of the PDO algorithm.
