Search Results for author:
Found 235 papers, 95 papers with code
Touch2Shape: Touch-Conditioned 3D Diffusion for Shape Exploration and Reconstruction
To overcome these limitations, we utilize tactile images to capture the local 3D information and propose a Touch2Shape model, which leverages a touch-conditioned diffusion model to explore and reconstruct the target shape from touch.
Incorporating brain-inspired mechanisms for multimodal learning in artificial intelligence
Inspired by this biological mechanism, we explore the relationship between multimodal output and information from individual modalities, proposing an inverse effectiveness driven multimodal fusion (IEMF) strategy.
Deep Learning Advances in Vision-Based Traffic Accident Anticipation: A Comprehensive Review of Methods,Datasets,and Future Directions
Traffic accident prediction and detection are critical for enhancing road safety, and vision-based traffic accident anticipation (Vision-TAA) has emerged as a promising approach in the era of deep learning. This paper reviews 147 recent studies, focusing on the application of supervised, unsupervised, and hybrid deep learning models for accident prediction, alongside the use of real-world and synthetic datasets. Current methodologies are categorized into four key approaches: image and video feature-based prediction, spatiotemporal feature-based prediction, scene understanding, and multimodal data fusion. While these methods demonstrate significant potential, challenges such as data scarcity, limited generalization to complex scenarios, and real-time performance constraints remain prevalent.
DiMeR: Disentangled Mesh Reconstruction Model
As for texture branch, we use RGB images as input to obtain the textured mesh.
DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB Image
To address these challenges, we propose a novel completion-based method, named DEPTHOR, featuring advances in both the training strategy and model architecture.
Flip Learning: Weakly Supervised Erase to Segment Nodules in Breast Ultrasound
(3) Implementation of a progressive curriculum learning strategy to enable agents to interact with the environment in a progressively challenging manner, thereby enhancing learning efficiency.
Iterative Optimal Attention and Local Model for Single Image Rain Streak Removal
To address these limitations, we propose an Expectation Maximization Reconstruction Transformer (EMResformer) for single image rain streak removal.
FetalFlex: Anatomy-Guided Diffusion Model for Flexible Control on Fetal Ultrasound Image Synthesis
Fetal ultrasound (US) examinations require the acquisition of multiple planes, each providing unique diagnostic information to evaluate fetal development and screening for congenital anomalies.
BAT: Learning Event-based Optical Flow with Bidirectional Adaptive Temporal Correlation
Event cameras deliver visual information characterized by a high dynamic range and high temporal resolution, offering significant advantages in estimating optical flow for complex lighting conditions and fast-moving objects.
BANet: Bilateral Aggregation Network for Mobile Stereo Matching
State-of-the-art stereo matching methods typically use costly 3D convolutions to aggregate a full cost volume, but their computational demands make mobile deployment challenging.
Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation
The normal maps are then used to reconstruct a 3D mesh, and the multi-view images provide texture mapping, resulting in a complete 3D model.
SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion
However, due to the manufacturing constraints of compact devices and the inherent physical principles of imaging, dToF depth maps are sparse and noisy.
Exploring Open-world Continual Learning with Knowns-Unknowns Knowledge Transfer
Particularly, our HoliTrans effectively supports knowledge transfer for both known and unknown samples while dynamically updating representations of open samples during OWCL.
Order-Robust Class Incremental Learning: Graph-Driven Dynamic Similarity Grouping
In response, we first provide additional theoretical analysis, which reveals that when the similarity among a group of classes is lower, the model demonstrates increased robustness to the class order.
Enhancing Audio-Visual Spiking Neural Networks through Semantic-Alignment and Cross-Modal Residual Learning
However, existing SNN models primarily focus on unimodal processing and lack efficient cross-modal information fusion, thereby limiting their effectiveness in real-world multimodal scenarios.
Ten Challenging Problems in Federated Foundation Models
This paper provides a comprehensive summary of the ten challenging problems inherent in FedFMs, encompassing foundational theory, utilization of private data, continual learning, unlearning, Non-IID and graph data, bidirectional knowledge transfer, incentive mechanism design, game mechanism design, model watermarking, and efficiency.
StereoGen: High-quality Stereo Image Generation from a Single Image
This pipeline utilizes arbitrary single images as left images and pseudo disparities generated by a monocular depth estimation model to synthesize high-quality corresponding right images.
MonSter: Marry Monodepth to Stereo Unleashes Power
The refined monodepth is in turn guides stereo effectively at ill-posed regions.
A New Perspective on Privacy Protection in Federated Learning with Granular-Ball Computing
Federated Learning (FL) facilitates collaborative model training while prioritizing privacy by avoiding direct data sharing.
Hgformer: Hyperbolic Graph Transformer for Recommendation
The cold start problem is a challenging problem faced by most modern recommender systems.
Introducing Semantic Capability in LinkedIn's Content Search Engine
In the past, most search queries issued to a search engine were short and simple.
Addressing Spatial-Temporal Data Heterogeneity in Federated Continual Learning via Tail Anchor
Federated continual learning (FCL) allows each client to continually update its knowledge from task streams, enhancing the applicability of federated learning in real-world scenarios.
FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagation
In this paper, we propose a novel global-aware scene flow estimation network with global motion propagation, named FlowMamba.
Leveraging Consistent Spatio-Temporal Correspondence for Robust Visual Odometry
Recent approaches to VO have significantly improved performance by using deep networks to predict optical flow between video frames.
Efficient MedSAMs: Segment Anything in Medical Images on Laptop
Promptable segmentation foundation models have emerged as a transformative approach to addressing the diverse needs in medical images, but most existing models require expensive computing, posing a big barrier to their adoption in clinical practice.
Guided Diffusion Model for Sensor Data Obfuscation
Sensor data collected by Internet of Things (IoT) devices carries detailed information about individuals in their vicinity.
Unleashing the Power of Continual Learning on Non-Centralized Devices: A Survey
To achieve high reliability and scalability in deploying this paradigm in distributed systems, it is essential to conquer challenges stemming from both spatial and temporal dimensions, manifesting as distribution shifts, catastrophic forgetting, heterogeneity, and privacy issues.
Multi-Granularity Open Intent Classification via Adaptive Granular-Ball Decision Boundary
To tackle these issues, we propose a Multi-granularity Open intent classification method via adaptive Granular-Ball decision boundary (MOGB).
RoMeO: Robust Metric Visual Odometry
We propose Robust Metric Visual Odometry (RoMeO), a novel method that resolves these issues leveraging priors from pre-trained depth models.
Biomass phenotyping of oilseed rape through UAV multi-view oblique imaging with 3DGS and SAM model
The SAM module achieved high segmentation accuracy, with a mean intersection over union (mIoU) of 0. 961 and an F1-score of 0. 980.
3D Multi-Object Tracking with Semi-Supervised GRU-Kalman Filter
3D Multi-Object Tracking (MOT), a fundamental component of environmental perception, is essential for intelligent systems like autonomous driving and robotic sensing.
Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priors
We propose bridging the gap between 2D and 3D diffusion models to address this limitation by integrating a two-stage frequency-based distillation loss with Gaussian Splatting.
Labeled-to-Unlabeled Distribution Alignment for Partially-Supervised Multi-Organ Medical Image Segmentation
However, the limited availability of labeled foreground organs and the absence of supervision to distinguish unlabeled foreground organs from the background pose a significant challenge, which leads to a distribution mismatch between labeled and unlabeled pixels.
IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching
We further propose a selective geometry feature fusion module to adaptively fuse multi-range and multi-granularity geometry features in MGEV.
PanicleNeRF: low-cost, high-precision in-field phenotypingof rice panicles with smartphone
The rice panicle traits significantly influence grain yield, making them a primary target for rice phenotyping studies.
CACE-Net: Co-guidance Attention and Contrastive Enhancement for Effective Audio-Visual Event Localization
Specifically, we have enhanced the model's ability to discern subtle differences between event and background and improved the accuracy of event classification in our model.
Explainable and Controllable Motion Curve Guided Cardiac Ultrasound Video Generation
In this context, we propose an explainable and controllable method for echocardiography video generation, taking an initial frame and a motion curve as guidance.
Mitral Regurgitation Recognition based on Unsupervised Out-of-Distribution Detection with Residual Diffusion Amplification
Since MR data is limited and has large intra-class variability, we propose an unsupervised out-of-distribution (OOD) detection method to identify MR rather than building a deep classifier.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Robust Box Prompt based SAM for Medical Image Segmentation
In this study, we propose a novel Robust Box prompt based SAM (\textbf{RoBox-SAM}) to ensure SAM's segmentation performance under prompts with different qualities.
PASSION: Towards Effective Incomplete Multi-Modal Medical Image Segmentation with Imbalanced Missing Rates
In this paper, we, for the first time, formulate such a challenging setting and propose Preference-Aware Self-diStillatION (PASSION) for incomplete multi-modal medical image segmentation under imbalanced missing rates.
Fine-grained Context and Multi-modal Alignment for Freehand 3D Ultrasound Reconstruction
In this context, we propose a novel method to exploit the long-range dependency management capabilities of the state space model (SSM) to address the above challenge.
FedIA: Federated Medical Image Segmentation with Heterogeneous Annotation Completeness
We begin by evaluating the completeness of annotations at the client level using a designed indicator.
Personalized Federated Continual Learning via Multi-granularity Prompt
In addition, we design a selective prompt fusion mechanism for aggregating knowledge of global prompts distilled from different clients.
FedMLP: Federated Multi-Label Medical Image Classification under Task Heterogeneity
Experiments on two publicly-available medical datasets validate the superiority of FedMLP against the state-of-the-art both federated semi-supervised and noisy label learning approaches under task heterogeneity.
Hyperbolic Knowledge Transfer in Cross-Domain Recommendation System
Cross-Domain Recommendation (CDR) seeks to utilize knowledge from different domains to alleviate the problem of data sparsity in the target recommendation domain, and it has been gaining more attention in recent years.
Apprenticeship-Inspired Elegance: Synergistic Knowledge Distillation Empowers Spiking Neural Networks for Efficient Single-Eye Emotion Recognition
We introduce a novel multimodality synergistic knowledge distillation scheme tailored for efficient single-eye motion recognition tasks.
IFTD: Image Feature Triangle Descriptor for Loop Detection in Driving Scenes
In this work, we propose a fast and robust Image Feature Triangle Descriptor (IFTD) based on the STD method, aimed at improving the efficiency and accuracy of place recognition in driving scenarios.
UniUSNet: A Promptable Framework for Universal Ultrasound Disease Prediction and Tissue Segmentation
Ultrasound is widely used in clinical practice due to its affordability, portability, and safety.
Optimization of Worker Scheduling at Logistics Depots Using Genetic Algorithms and Simulated Annealing
This paper addresses the optimization of scheduling for workers at a logistics depot using a combination of genetic algorithm and simulated annealing algorithm.
FedProK: Trustworthy Federated Class-Incremental Learning via Prototypical Feature Knowledge Transfer
Federated Class-Incremental Learning (FCIL) focuses on continually transferring the previous knowledge to learn new classes in dynamic Federated Learning (FL).
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.
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
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.
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.
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.
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.
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.
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.
FlowDA: Unsupervised Domain Adaptive Framework for Optical Flow Estimation
This paper introduces FlowDA, an unsupervised domain adaptive (UDA) framework for optical flow estimation.
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.
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.
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).
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.
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.
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.
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.
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.
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.
IBoxCLA: Towards Robust Box-supervised Segmentation of Polyp via Improved Box-dice and Contrastive Latent-anchors
In response, we propose two innovative learning fashions, Improved Box-dice (IBox) and Contrastive Latent-Anchors (CLA), and combine them to train a robust box-supervised model IBoxCLA.
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 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.
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.
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.
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.
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.
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.
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.
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.
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.
Fast Quantum Algorithm for Attention Computation
It is well-known that quantum machine has certain computational advantages compared to the classical machine.
FreeCOS: Self-Supervised Learning from Fractals and Unlabeled Images for Curvilinear Object Segmentation
Curvilinear object segmentation is critical for many applications.
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.
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.
DIAS: A Dataset and Benchmark for Intracranial Artery Segmentation in DSA sequences
In this work, we introduce DIAS, a dataset specifically developed for IA segmentation in DSA sequences.
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.
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.
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.
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.
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.
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.
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.
Differentially Private Attention Computation
Large language models (LLMs), especially those based on the Transformer architecture, have had a profound impact on various aspects of daily life, such as natural language processing, content generation, research methodologies, and more.
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.
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.
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.
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.
Ranked #3 on
Omnnidirectional Stereo Depth Estimation
on Helvipad
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.
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.
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.
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).
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.
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.
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.
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.
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.
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.
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.
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.
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
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).
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.
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.
Explore Contextual Information for 3D Scene Graph Generation
3D scene graph generation (SGG) has been of high interest in computer vision.
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.
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.
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.
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).
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.
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.
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.
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
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.
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.
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.
Online Reflective Learning for Robust Medical Image Segmentation
Deep segmentation models often face the failure risks when the testing image presents unseen distributions.
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.
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.
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.
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.
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 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.
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.
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.
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.
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.
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.
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
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).
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.
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.
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 #2 on
Camouflaged Object Segmentation
on PCOD_1200
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.
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?
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.
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.
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.
Monocular Depth Estimation with Sharp Boundary
In order to mitigate the boundary blur problem, we focus on the above two impact factors.
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
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.
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.
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.
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.
Flip Learning: Erase to Segment
Weakly-supervised segmentation (WSS) can help reduce time-consuming and cumbersome manual annotation.
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.
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.
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.
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.
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.
LENAS: Learning-based Neural Architecture Search and Ensemble for 3D Radiotherapy Dose Prediction
To mitigate the complexity introduced by the model ensemble, we adopt the teacher-student paradigm, leveraging the diverse outputs from multiple learned networks as supervisory signals to guide the training of the student network.
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.
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.
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.
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.
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.
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.
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 #10 on
Camouflaged Object Segmentation
on PCOD_1200
Camouflaged Object Segmentation
Dichotomous Image Segmentation
+3
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.
Smart Scribbles for Image Mating
Image matting is an ill-posed problem that usually requires additional user input, such as trimaps or scribbles.
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.
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.
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.
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.
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.
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.
Tripartite Information Mining and Integration for Image Matting
Regarding the nature of image matting, most researches have focused on solutions for transition regions.
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.
Contrastive Rendering for Ultrasound Image Segmentation
However, the lack of sharp boundaries in US images still remains an inherent challenge for segmentation.
Weakly-supervised Salient Instance Detection
Inspired by this insight, we propose to use class and subitizing labels as weak supervision for the SID problem.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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).
FetusMap: Fetal Pose Estimation in 3D Ultrasound
(i) This is the first work about 3D pose estimation of fetus in the literature.
