Search Results for author:
Found 221 papers, 64 papers with code
Modeling Aspect Correlation for Aspect-based Sentiment Analysis via Recurrent Inverse Learning Guidance
Second, we propose Inverse Learning Guidance to improve the selection of aspect feature by considering aspect correlation, which provides more useful information to determine polarity.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
A robot foundation model, trained on massive and diverse data sources, is essential for enabling the robots to reason about novel situations, robustly handle real-world variability, and rapidly learn new tasks.
Weakly Supervised Spatial Implicit Neural Representation Learning for 3D MRI-Ultrasound Deformable Image Registration in HDR Prostate Brachytherapy
For the institutional dataset, prostate CTV achieved DSC $0. 88 \pm 0. 09$, MSD $1. 21 \pm 0. 38$ mm, and HD95 $2. 09 \pm 1. 48$ mm.
Error Analyses of Auto-Regressive Video Diffusion Models: A Unified Framework
In this work, we develop theoretical underpinnings for these models and use our insights to improve the performance of existing models.
Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update
We study the stochastic linear bandits with heavy-tailed noise.
RelaCtrl: Relevance-Guided Efficient Control for Diffusion Transformers
The Diffusion Transformer plays a pivotal role in advancing text-to-image and text-to-video generation, owing primarily to its inherent scalability.
NVR: Vector Runahead on NPUs for Sparse Memory Access
In this paper, we present NPU Vector Runahead (NVR), a prefetching mechanism tailored for NPUs to address cache miss problems in sparse DNN workloads.
FuncGenFoil: Airfoil Generation and Editing Model in Function Space
Aircraft manufacturing is the jewel in the crown of industry, among which generating high-fidelity airfoil geometries with controllable and editable representations remains a fundamental challenge.
The Joint Entity-Relation Extraction Model Based on Span and Interactive Fusion Representation for Chinese Medical Texts with Complex Semantics
Additionally, to address the inefficiencies of existing methods in facilitating information exchange between entity recognition and relation extraction, we present an interactive fusion representation module.
Segmentation-Aware Generative Reinforcement Network (GRN) for Tissue Layer Segmentation in 3-D Ultrasound Images for Chronic Low-back Pain (cLBP) Assessment
We introduce a novel segmentation-aware joint training framework called generative reinforcement network (GRN) that integrates segmentation loss feedback to optimize both image generation and segmentation performance in a single stage.
A two-stage dual-task learning strategy for early prediction of pathological complete response to neoadjuvant chemotherapy for breast cancer using dynamic contrast-enhanced magnetic resonance images
To improve prediction accuracy at the early time point of neoadjuvant chemotherapy, we proposed a two-stage dual-task learning strategy to train a deep neural network for early prediction of pCR using early-treatment magnetic resonance images.
A Survey of Optimization Methods for Training DL Models: Theoretical Perspective on Convergence and Generalization
In this paper, we provide an extensive summary of the theoretical foundations of optimization methods in DL, including presenting various methodologies, their convergence analyses, and generalization abilities.
Online Video Understanding: A Comprehensive Benchmark and Memory-Augmented Method
This framework led to the development of VideoChat-Online, a robust and efficient model for online video understanding.
A Fluid-Structure Interaction Model of the Zebrafish Aortic Valve
Computational fluid-structure interaction (FSI) simulations are an efficient and highly controllable means to study the function of cardiac valves in development and diseases.
What Has Been Overlooked in Contrastive Source-Free Domain Adaptation: Leveraging Source-Informed Latent Augmentation within Neighborhood Context
The absence of access to source data during adaptation makes it challenging to analytically estimate the domain gap.
Dynamic Try-On: Taming Video Virtual Try-on with Dynamic Attention Mechanism
The primary challenges in this domain are twofold: (1) leveraging the garment encoder's capabilities in video try-on while lowering computational requirements; (2) ensuring temporal consistency in the synthesis of human body parts, especially during rapid movements.
Hesitation and Tolerance in Recommender Systems
We integrated these insights into the training process of a recommender system for a major short-video platform.
CoDTS: Enhancing Sparsely Supervised Collaborative Perception with a Dual Teacher-Student Framework
Extensive experiments demonstrate that the CoDTS effectively ensures an optimal balance of pseudo labels in both quality and quantity, establishing a new state-of-the-art in sparsely supervised collaborative perception.
A multimodal ensemble approach for clear cell renal cell carcinoma treatment outcome prediction
Using predicted risk medians to stratify high- and low-risk groups, log-rank tests showed improved performance in both OS and DFS compared to single-modality models.
HSLiNets: Hyperspectral Image and LiDAR Data Fusion Using Efficient Dual Non-Linear Feature Learning Networks
The integration of hyperspectral imaging (HSI) and LiDAR data within new linear feature spaces offers a promising solution to the challenges posed by the high-dimensionality and redundancy inherent in HSIs.
Hyperspectral Images Efficient Spatial and Spectral non-Linear Model with Bidirectional Feature Learning
Classifying hyperspectral images (HSIs) is a complex task in remote sensing due to the high-dimensional nature and volume of data involved.
Act Now: A Novel Online Forecasting Framework for Large-Scale Streaming Data
2) Eliminating information leakage can exacerbate concept drift and online parameter updates can damage prediction accuracy.
An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion Models
Moreover, thanks to CNF, CDSegNet can generate the semantic labels in a single-step inference like non-DDPMs, due to avoiding directly fitting the scores from semantic labels in the dominant network of CDSegNet.
Large-scale cross-modality pretrained model enhances cardiovascular state estimation and cardiomyopathy detection from electrocardiograms: An AI system development and multi-center validation study
Cardiovascular diseases (CVDs) present significant challenges for early and accurate diagnosis.
Model Editing for LLMs4Code: How Far are We?
Despite that, a comprehensive study that thoroughly compares and analyzes the performance of the state-of-the-art model editing techniques for adapting the knowledge within LLMs4Code across various code-related tasks is notably absent.
HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference
We present HOBBIT, a mixed precision expert offloading system to enable flexible and efficient MoE inference.
Redefining <Creative> in Dictionary: Towards an Enhanced Semantic Understanding of Creative Generation
``Creative'' remains an inherently abstract concept for both humans and diffusion models.
Generalized Multimodal Fusion via Poisson-Nernst-Planck Equation
Building on these theoretical foundations, GMF disassociated features which extracted by the unimodal feature extractor into modality-specific and modality-invariant subspaces, thereby reducing mutual information and subsequently lowering the entropy of downstream tasks.
Towards Better Performance in Incomplete LDL: Addressing Data Imbalance
Label Distribution Learning (LDL) is a novel machine learning paradigm that addresses the problem of label ambiguity and has found widespread applications.
FINE: Factorizing Knowledge for Initialization of Variable-sized Diffusion Models
Diffusion models often face slow convergence, and existing efficient training techniques, such as Parameter-Efficient Fine-Tuning (PEFT), are primarily designed for fine-tuning pre-trained models.
DiffFluid: Plain Diffusion Models are Effective Predictors of Flow Dynamics
We showcase the plain diffusion models with Transformers are effective predictors of fluid dynamics under various working conditions, e. g., Darcy flow and high Reynolds number.
Qihoo-T2X: An Efficient Proxy-Tokenized Diffusion Transformer for Text-to-Any-Task
The global self-attention mechanism in diffusion transformers involves redundant computation due to the sparse and redundant nature of visual information, and the attention map of tokens within a spatial window shows significant similarity.
Prompt-Softbox-Prompt: A free-text Embedding Control for Image Editing
First, while the 'aug_embedding' captures the full semantic content of the text, its contribution to the final image generation is relatively minor.
FancyVideo: Towards Dynamic and Consistent Video Generation via Cross-frame Textual Guidance
Then, TAR refines the correlation matrix between cross-frame textual conditions and latent features along the time dimension.
KIND: Knowledge Integration and Diversion in Diffusion Models
Results indicate that KIND achieves state-of-the-art performance compared to other PEFT and learngene methods.
BeyondCT: A deep learning model for predicting pulmonary function from chest CT scans
The BeyondCT model without demographics had MAEs of 0. 362 L and 0. 371 L, percentage errors of 10. 89% and 14. 96%, and R square of 0. 719 and 0. 727, respectively.
A Labeled Ophthalmic Ultrasound Dataset with Medical Report Generation Based on Cross-modal Deep Learning
It collects three modal data, including the ultrasound images, blood flow information and examination reports from 2, 417 patients at an ophthalmology hospital in Shenyang, China, during the year 2018, in which the patient information is de-identified for privacy protection.
UMono: Physical Model Informed Hybrid CNN-Transformer Framework for Underwater Monocular Depth Estimation
Underwater monocular depth estimation serves as the foundation for tasks such as 3D reconstruction of underwater scenes.
Static and multivariate-temporal attentive fusion transformer for readmission risk prediction
Methods:We propose a novel static and multivariate-temporal attentive fusion transformer (SMTAFormer) to predict short-term readmission of ICU patients by fully leveraging the potential of demographic and dynamic temporal data.
VideoEval: Comprehensive Benchmark Suite for Low-Cost Evaluation of Video Foundation Model
With the growth of high-quality data and advancement in visual pre-training paradigms, Video Foundation Models (VFMs) have made significant progress recently, demonstrating their remarkable performance on traditional video understanding benchmarks.
TVR-Ranking: A Dataset for Ranked Video Moment Retrieval with Imprecise Queries
To facilitate research in RVMR, we develop the TVR-Ranking dataset, based on the raw videos and existing moment annotations provided in the TVR dataset.
Open-Event Procedure Planning in Instructional Videos
Specifically, in this paper, we introduce a new task named Open-event Procedure Planning (OEPP), which extends the traditional procedure planning to the open-event setting.
LANE: Logic Alignment of Non-tuning Large Language Models and Online Recommendation Systems for Explainable Reason Generation
The explainability of recommendation systems is crucial for enhancing user trust and satisfaction.
WAVE: Weight Template for Adaptive Initialization of Variable-sized Models
During initialization, target models will initialize the corresponding weight scalers tailored to their model size, which are sufficient to learn the connection rules of weight templates based on the Kronecker product from a limited amount of data.
CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control
Retrieval-augmented generation (RAG) has emerged as a promising solution for mitigating hallucinations of large language models (LLMs) with retrieved external knowledge.
Predicting Many Crystal Properties via an Adaptive Transformer-based Framework
Machine learning has revolutionized many fields, including materials science.
Inaccurate Label Distribution Learning with Dependency Noise
In this paper, we introduce the Dependent Noise-based Inaccurate Label Distribution Learning (DN-ILDL) framework to tackle the challenges posed by noise in label distribution learning, which arise from dependencies on instances and labels.
Talk to Parallel LiDARs: A Human-LiDAR Interaction Method Based on 3D Visual Grounding
LiDAR sensors play a crucial role in various applications, especially in autonomous driving.
Adjacent Leader Decentralized Stochastic Gradient Descent
This work focuses on the decentralized deep learning optimization framework.
Advancing Head and Neck Cancer Survival Prediction via Multi-Label Learning and Deep Model Interpretation
We also present Grad-TEAM, a Gradient-weighted Time-Event Activation Mapping approach specifically developed for deep survival model visual explanation, to generate patient-specific time-to-event activation maps.
TransAnaNet: Transformer-based Anatomy Change Prediction Network for Head and Neck Cancer Patient Radiotherapy
The predicted image from the proposed method yielded the best similarity to the real image (CBCT21) over pCT, CBCT01, and predicted CBCTs from other comparison models.
GaitMotion: A Multitask Dataset for Pathological Gait Forecasting
The wearable gait analysis suit captures the gait cycle, pattern, and parameters for both normal and pathological subjects.
Towards Coarse-to-Fine Evaluation of Inference Efficiency for Large Language Models
In real world, large language models (LLMs) can serve as the assistant to help users accomplish their jobs, and also support the development of advanced applications.
Unsupervised Band Selection Using Fused HSI and LiDAR Attention Integrating With Autoencoder
These approaches overlook the potential benefits of integrating multiple data sources, such as Light Detection and Ranging (LiDAR), and is further challenged by the limited availability of labeled data in HSI processing, which represents a significant obstacle.
LiDAR-Guided Cross-Attention Fusion for Hyperspectral Band Selection and Image Classification
The fusion of hyperspectral and LiDAR data has been an active research topic.
HSIMamba: Hyperpsectral Imaging Efficient Feature Learning with Bidirectional State Space for Classification
HSIMamba is designed to process data bidirectionally, significantly enhancing the extraction of spectral features and integrating them with spatial information for comprehensive analysis.
Empowering Segmentation Ability to Multi-modal Large Language Models
Multi-modal large language models (MLLMs) can understand image-language prompts and demonstrate impressive reasoning ability.
Bit Rate Matching Algorithm Optimization in JPEG-AI Verification Model
To generate reconstructed images with the desired bits per pixel and assess the BD-rate performance of both the JPEG-AI verification model and VVC intra, bit rate matching is employed.
Hierarchical Prior-based Super Resolution for Point Cloud Geometry Compression
The content-dependent hierarchical prior is constructed at the encoder side, which enables coarse-to-fine super resolution of the point cloud geometry at the decoder side.
ClickSAM: Fine-tuning Segment Anything Model using click prompts for ultrasound image segmentation
ClickSAM has two stages of training: the first stage is trained on single-click prompts centered in the ground-truth contours, and the second stage focuses on improving the model performance through additional positive and negative click prompts.
A Novel Paradigm in Solving Multiscale Problems
By enabling the acquisition of large-scale data with minimal computational demands, coupled with the efficient and accurate characterization of small-scale dynamics via Spectral PINN, our approach offers a valuable and promising approach for researchers seeking to tackle multiscale phenomena effectively.
Data Distribution Dynamics in Real-World WiFi-Based Patient Activity Monitoring for Home Healthcare
This paper examines the application of WiFi signals for real-world monitoring of daily activities in home healthcare scenarios.
SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering
In particular, local editing methods, which directly update model parameters, are more suitable for updating a small amount of knowledge.
Weaver: Foundation Models for Creative Writing
Weaver is pre-trained on a carefully selected corpus that focuses on improving the writing capabilities of large language models.
Transferring Core Knowledge via Learngenes
GTL trains a population of networks, selects superior learngenes by tournaments, performs learngene mutations, and passes the learngenes to next generations.
Nurse-in-the-Loop Artificial Intelligence for Precision Management of Type 2 Diabetes in a Clinical Trial Utilizing Transfer-Learned Predictive Digital Twin
Participants were randomly assigned to an intervention (AI, n=10) group to receive daily AI-generated individualized feedback or a control group without receiving the daily feedback (non-AI, n=10) in the last three months.
Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype Enhancement
In this paper, we propose a novel framework based on the adapter mechanism, namely Adaptive FSS, which can efficiently adapt the existing FSS model to the novel classes.
Graph Attention-Based Symmetry Constraint Extraction for Analog Circuits
In recent years, analog circuits have received extensive attention and are widely used in many emerging applications.
DMT: Comprehensive Distillation with Multiple Self-supervised Teachers
Numerous self-supervised learning paradigms, such as contrastive learning and masked image modeling, have been proposed to acquire powerful and general representations from unlabeled data.
Time-Series Contrastive Learning against False Negatives and Class Imbalance
As an exemplary self-supervised approach for representation learning, time-series contrastive learning has exhibited remarkable advancements in contemporary research.
RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Inter-label Correlations
This paper introduces RankMatch, an innovative approach for Semi-Supervised Label Distribution Learning (SSLDL).
PneumoLLM: Harnessing the Power of Large Language Model for Pneumoconiosis Diagnosis
Yet, this approach often requires optimization of extensive learnable parameters in the text branch and the dialogue head, potentially diminishing the LLMs' efficacy, especially with limited training data.
Manipulating the Label Space for In-Context Classification
Specifically, using our approach on ImageNet, we increase accuracy from 74. 70\% in a 4-shot setting to 76. 21\% with just 2 shots.
Automated interpretation of congenital heart disease from multi-view echocardiograms
Our video-based model can diagnose with an accuracy of 93. 9\% (binary classification), and 92. 1\% (3-class classification) in a collected 2D video testing set, which does not need key-frame selection and view annotation in testing.
Toward the Tradeoffs between Privacy, Fairness and Utility in Federated Learning
Researchers have struggled to design fair FL systems that ensure fairness of results.
Key Issues in Wireless Transmission for NTN-Assisted Internet of Things
The long-distance wireless signal propagation in NTNs leads to severe path loss and large latency, where the accurate acquisition of channel state information (CSI) is another challenge, especially for fast-moving non-terrestrial base stations (NTBSs).
Language-guided Few-shot Semantic Segmentation
Few-shot learning is a promising way for reducing the label cost in new categories adaptation with the guidance of a small, well labeled support set.
Exploring Active Learning in Meta-Learning: Enhancing Context Set Labeling
Most meta-learning methods assume that the (very small) context set used to establish a new task at test time is passively provided.
High Visual-Fidelity Learned Video Compression
With the growing demand for video applications, many advanced learned video compression methods have been developed, outperforming traditional methods in terms of objective quality metrics such as PSNR.
A Unified View on Neural Message Passing with Opinion Dynamics for Social Networks
Drawing inspiration from opinion dynamics in sociology, we propose ODNet, a novel message passing scheme incorporating bounded confidence, to refine the influence weight of local nodes for message propagation.
nnSAM: Plug-and-play Segment Anything Model Improves nnUNet Performance
To combine the strengths of foundational and domain-specific models, we propose nnSAM, integrating SAM's robust feature extraction with nnUNet's automatic configuration to enhance segmentation accuracy on small datasets.
Unsupervised Contrast-Consistent Ranking with Language Models
We compare pairwise, pointwise and listwise prompting techniques to elicit a language model's ranking knowledge.
Recurrence-Free Survival Prediction for Anal Squamous Cell Carcinoma Chemoradiotherapy using Planning CT-based Radiomics Model
Conclusions: A treatment planning CT based radiomics and clinical combined model had improved prognostic performance in predicting RFS for ASCC patients treated with CRT as compared to a model using clinical features only.
Frequency Compensated Diffusion Model for Real-scene Dehazing
In this paper, we consider a dehazing framework based on conditional diffusion models for improved generalization to real haze.
Video Captioning with Aggregated Features Based on Dual Graphs and Gated Fusion
The application of video captioning models aims at translating the content of videos by using accurate natural language.
ES-MVSNet: Efficient Framework for End-to-end Self-supervised Multi-View Stereo
to provide additional consistency constraints, which grows GPU memory consumption and complicates the model's structure and training pipeline.
Dynamic Token-Pass Transformers for Semantic Segmentation
Vision transformers (ViT) usually extract features via forwarding all the tokens in the self-attention layers from top to toe.
A Hybrid Optimization and Deep Learning Algorithm for Cyber-resilient DER Control
To this end, a hybrid feedback-based optimization algorithm along with deep learning forecasting technique is proposed to specifically address the cyber-related issues.
How Does Diffusion Influence Pretrained Language Models on Out-of-Distribution Data?
It shows that finetuning PLMs with diffusion degrades the reconstruction ability on OOD data.
Rethinking Mitosis Detection: Towards Diverse Data and Feature Representation
And the feature diversity is preserved by inter- and intra- class feature diversity-preserved module (InCDP).
Leveraging GPT-4 for Food Effect Summarization to Enhance Product-Specific Guidance Development via Iterative Prompting
Specifically, we propose a three-turn iterative prompting approach to food effect summarization in which the keyword-focused and length-controlled prompts are respectively provided in consecutive turns to refine the quality of the generated summary.
Genes in Intelligent Agents
Inspired by the biological intelligence, artificial intelligence (AI) has devoted to building the machine intelligence.
Automatic Deduction Path Learning via Reinforcement Learning with Environmental Correction
To this end, we formulate the problem as a partially observable Markov decision problem (POMDP) and employ an environment correction algorithm based on the characteristics of the business.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
MS-DETR: Natural Language Video Localization with Sampling Moment-Moment Interaction
Given a query, the task of Natural Language Video Localization (NLVL) is to localize a temporal moment in an untrimmed video that semantically matches the query.
Physics-Assisted Reduced-Order Modeling for Identifying Dominant Features of Transonic Buffet
The dominant latent space further reveals a strong relevance with the key flow features located in the boundary layers downstream of shock.
Tight and fast generalization error bound of graph embedding in metric space
However, recent theoretical analyses have shown a much higher upper bound on non-Euclidean graph embedding's generalization error than Euclidean one's, where a high generalization error indicates that the incompleteness and noise in the data can significantly damage learning performance.
Automated Grain Boundary (GB) Segmentation and Microstructural Analysis in 347H Stainless Steel Using Deep Learning and Multimodal Microscopy
We combine scanning electron microscopy (SEM) images of 347H stainless steel as training data and electron backscatter diffraction (EBSD) micrographs as pixel-wise labels for grain boundary detection as a semantic segmentation task.
Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Models
(i) Accumulating: the knowledge is accumulated during the continuous learning of an ancestry model.
Cross-Shaped Windows Transformer with Self-supervised Pretraining for Clinically Significant Prostate Cancer Detection in Bi-parametric MRI
We introduce a novel end-to-end Cross-Shaped windows (CSwin) transformer UNet model, CSwin UNet, to detect clinically significant prostate cancer (csPCa) in prostate bi-parametric MR imaging (bpMRI) and demonstrate the effectiveness of our proposed self-supervised pre-training framework.
FreMIM: Fourier Transform Meets Masked Image Modeling for Medical Image Segmentation
The research community has witnessed the powerful potential of self-supervised Masked Image Modeling (MIM), which enables the models capable of learning visual representation from unlabeled data.
Zero-shot Medical Image Translation via Frequency-Guided Diffusion Models
However, for medical image translation, the existing diffusion models are deficient in accurately retaining structural information since the structure details of source domain images are lost during the forward diffusion process and cannot be fully recovered through learned reverse diffusion, while the integrity of anatomical structures is extremely important in medical images.
Evidence-aware multi-modal data fusion and its application to total knee replacement prediction
For each branch, there is an evidence network that takes the extracted features as input and outputs an evidence score, which is designed to represent the reliability of the output from the current branch.
PPG-based Heart Rate Estimation with Efficient Sensor Sampling and Learning Models
Moreover, our analysis showed that DT models with 10 to 20 input features usually have good accuracy, while are several magnitude smaller in model sizes and faster in inference time.
Data Augmentation For Label Enhancement
Existing LE approach have the following problems: (\textbf{i}) They use logical label to train mappings to LD, but the supervision information is too loose, which can lead to inaccurate model prediction; (\textbf{ii}) They ignore feature redundancy and use the collected features directly.
Knowledge-embedded meta-learning model for lift coefficient prediction of airfoils
In the proposed model, a primary network is responsible for representing the relationship between the lift and angle of attack, while the geometry information is encoded into a hyper network to predict the unknown parameters involved in the primary network.
Revisiting Weighted Strategy for Non-stationary Parametric Bandits
We propose a refined analysis framework, which simplifies the derivation and importantly produces a simpler weight-based algorithm that is as efficient as window/restart-based algorithms while retaining the same regret as previous studies.
Inaccurate Label Distribution Learning
The previous LDL methods all assumed the LDs of the training instances are accurate.
Differentiable Arbitrating in Zero-sum Markov Games
We initiate the study of how to perturb the reward in a zero-sum Markov game with two players to induce a desirable Nash equilibrium, namely arbitrating.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Joint Beamforming and PD Orientation Design for Mobile Visible Light Communications
To address this challenge, we propose an alternating optimization algorithm to obtain the transmit beamforming and the PD orientation.
MF2-MVQA: A Multi-stage Feature Fusion method for Medical Visual Question Answering
There is a key problem in the medical visual question answering task that how to effectively realize the feature fusion of language and medical images with limited datasets.
Modified EDAS Method Based on Cumulative Prospect Theory for Multiple Attributes Group Decision Making with Interval-valued Intuitionistic Fuzzy Information
Taking the fuzzy and uncertain character of the IVIFSs and the psychological preference into consideration, the original EDAS method based on the CPT under IVIFSs (IVIF-CPT-MABAC) method is built for MAGDM issues.
Uncertainty estimations methods for a deep learning model to aid in clinical decision-making -- a clinician's perspective
Especially for smaller, single institutional datasets, it may be important to evaluate multiple estimations techniques before incorporating a model into clinical practice.
Recurrence-free Survival Prediction under the Guidance of Automatic Gross Tumor Volume Segmentation for Head and Neck Cancers
For Head and Neck Cancers (HNC) patient management, automatic gross tumor volume (GTV) segmentation and accurate pre-treatment cancer recurrence prediction are of great importance to assist physicians in designing personalized management plans, which have the potential to improve the treatment outcome and quality of life for HNC patients.
A Constrained Deformable Convolutional Network for Efficient Single Image Dynamic Scene Blind Deblurring with Spatially-Variant Motion Blur Kernels Estimation
Most existing deep-learning-based single image dynamic scene blind deblurring (SIDSBD) methods usually design deep networks to directly remove the spatially-variant motion blurs from one inputted motion blurred image, without blur kernels estimation.
AlphaVC: High-Performance and Efficient Learned Video Compression
With these powerful techniques, this paper proposes AlphaVC, a high-performance and efficient learned video compression scheme.
Content-oriented learned image compression
In recent years, with the development of deep neural networks, end-to-end optimized image compression has made significant progress and exceeded the classic methods in terms of rate-distortion performance.
Fine-Tuning BERT for Automatic ADME Semantic Labeling in FDA Drug Labeling to Enhance Product-Specific Guidance Assessment
Product-specific guidances (PSGs) recommended by the United States Food and Drug Administration (FDA) are instrumental to promote and guide generic drug product development.
Two-Stage Fine-Tuning: A Novel Strategy for Learning Class-Imbalanced Data
Owing to this paucity of samples, learning on the tail classes is especially challenging for the fine-tuning when transferring a pretrained model to a downstream task.
Positive-Negative Equal Contrastive Loss for Semantic Segmentation
The contextual information is critical for various computer vision tasks, previous works commonly design plug-and-play modules and structural losses to effectively extract and aggregate the global context.
Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition
Inspired by the observation that humans learn to recognize the texts through both reading and writing, we propose to learn discrimination and generation by integrating contrastive learning and masked image modeling in our self-supervised method.
Taxonomy and evolution predicting using deep learning in images
Molecular and morphological characters, as important parts of biological taxonomy, are contradictory but need to be integrated.
Med-DANet: Dynamic Architecture Network for Efficient Medical Volumetric Segmentation
For 3D medical image (e. g. CT and MRI) segmentation, the difficulty of segmenting each slice in a clinical case varies greatly.
Lesion classification by model-based feature extraction: A differential affine invariant model of soft tissue elasticity
The outcomes of this modeling approach reached the score of area under the curve of the receiver operating characteristics of 94. 2 % for the polyps and 87. 4 % for the nodules, resulting in an average gain of 5 % to 30 % over ten existing state-of-the-art lesion classification methods.
A Model Predictive Control Functional Continuous Time Bayesian Network for Self-Management of Multiple Chronic Conditions
Multiple chronic conditions (MCC) are one of the biggest challenges of modern times.
MSTRIQ: No Reference Image Quality Assessment Based on Swin Transformer with Multi-Stage Fusion
Many Image Quality Assessment(IQA) algorithms have been designed to tackle this problem.
A neural network model for timing control with reinforcement
How do humans and animals perform trial-and-error learning when the space of possibilities is infinite?
Parametric Generative Schemes with Geometric Constraints for Encoding and Synthesizing Airfoils
In contrast, the hard-constrained scheme produces airfoils with a wider range of geometric diversity while strictly adhering to the geometric constraints.
Ensemble diverse hypotheses and knowledge distillation for unsupervised cross-subject adaptation
EDH mitigates the divergence between labeled data of source subjects and unlabeled data of target subjects to accurately classify the locomotion modes of target subjects without labeling data.
BIOS: An Algorithmically Generated Biomedical Knowledge Graph
For decades, these knowledge graphs have been developed via expert curation; however, this method can no longer keep up with today's AI development, and a transition to algorithmically generated BioMedKGs is necessary.
Undersampled MRI Reconstruction with Side Information-Guided Normalisation
In this paper, we investigate the use of such side information as normalisation parameters in a convolutional neural network (CNN) to improve undersampled MRI reconstruction.
TransBTSV2: Towards Better and More Efficient Volumetric Segmentation of Medical Images
Different from TransBTS, the proposed TransBTSV2 is not limited to brain tumor segmentation (BTS) but focuses on general medical image segmentation, providing a stronger and more efficient 3D baseline for volumetric segmentation of medical images.
Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape
In this paper, we study the sharpness of a deep learning (DL) loss landscape around local minima in order to reveal systematic mechanisms underlying the generalization abilities of DL models.
Preserving Domain Private Representation via Mutual Information Maximization
Recent advances in unsupervised domain adaptation have shown that mitigating the domain divergence by extracting the domain-invariant representation could significantly improve the generalization of a model to an unlabeled data domain.
Generalization Bounds for Graph Embedding Using Negative Sampling: Linear vs Hyperbolic
Graph embedding, which represents real-world entities in a mathematical space, has enabled numerous applications such as analyzing natural languages, social networks, biochemical networks, and knowledge bases. It has been experimentally shown that graph embedding in hyperbolic space can represent hierarchical tree-like data more effectively than embedding in linear space, owing to hyperbolic space's exponential growth property.
AutoDrop: Training Deep Learning Models with Automatic Learning Rate Drop
Modern deep learning (DL) architectures are trained using variants of the SGD algorithm that is run with a $\textit{manually}$ defined learning rate schedule, i. e., the learning rate is dropped at the pre-defined epochs, typically when the training loss is expected to saturate.
Video Text Tracking With a Spatio-Temporal Complementary Model
We leverage a Siamese ComplementaryModule to fully exploit the continuity characteristic of the textinstances in the temporal dimension, which effectively alleviatesthe missed detection of the text instances, and hence ensuresthe completeness of each text trajectory.
SleepPriorCL: Contrastive Representation Learning with Prior Knowledge-based Positive Mining and Adaptive Temperature for Sleep Staging
The objective of this paper is to learn semantic representations for sleep stage classification from raw physiological time series.
Memory-augmented Adversarial Autoencoders for Multivariate Time-series Anomaly Detection with Deep Reconstruction and Prediction
Recent progress of unsupervised time-series anomaly detection mainly use deep autoencoders to solve this problem, i. e. training on normal samples and producing significant reconstruction error on abnormal inputs.
Accelerating Multi-Objective Neural Architecture Search by Random-Weight Evaluation
For the goal of automated design of high-performance deep convolutional neural networks (CNNs), Neural Architecture Search (NAS) methodology is becoming increasingly important for both academia and industries. Due to the costly stochastic gradient descent (SGD) training of CNNs for performance evaluation, most existing NAS methods are computationally expensive for real-world deployments.
Can standard training with clean images outperform adversarial one in robust accuracy?
Thus the perturbations carefully generated by the attacker can be diminished.
Multi-View Spatial-Temporal Graph Convolutional Networks with Domain Generalization for Sleep Stage Classification
To address the above challenges, we propose a multi-view spatial-temporal graph convolutional networks (MSTGCN) with domain generalization for sleep stage classification.
Discriminative Semantic Feature Pyramid Network with Guided Anchoring for Logo Detection
Unlike general object detection, logo detection is a challenging task, especially for small logo objects and large aspect ratio logo objects in the real-world scenario.
From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network
Such operation guides the vision model to use not only the visual texture of characters, but also the linguistic information in visual context for recognition when the visual cues are confused (e. g. occlusion, noise, etc.).
PASTO: Strategic Parameter Optimization in Recommendation Systems -- Probabilistic is Better than Deterministic
In this setting with multiple and constrained goals, this paper discovers that a probabilistic strategic parameter regime can achieve better value compared to the standard regime of finding a single deterministic parameter.
FoodLogoDet-1500: A Dataset for Large-Scale Food Logo Detection via Multi-Scale Feature Decoupling Network
For that, we propose a novel food logo detection method Multi-scale Feature Decoupling Network (MFDNet), which decouples classification and regression into two branches and focuses on the classification branch to solve the problem of distinguishing multiple food logo categories.
HetEmotionNet: Two-Stream Heterogeneous Graph Recurrent Neural Network for Multi-modal Emotion Recognition
The research on human emotion under multimedia stimulation based on physiological signals is an emerging field, and important progress has been achieved for emotion recognition based on multi-modal signals.
Multi-Channel Auto-Encoders and a Novel Dataset for Learning Domain Invariant Representations of Histopathology Images
Experimental results show that the MCAE model produces feature representations that are less sensitive to inter-domain variations than the comparative StaNoSA method when tested on the novel synthetic data.
Nonlinear State Space Modeling and Control of the Impact of Patients' Modifiable Lifestyle Behaviors on the Emergence of Multiple Chronic Conditions
The emergence and progression of multiple chronic conditions (MCC) over time often form a dynamic network that depends on patient's modifiable risk factors and their interaction with non-modifiable risk factors and existing conditions.
Improving OCR-Based Image Captioning by Incorporating Geometrical Relationship
Under the guidance of the geometrical relationship between OCR tokens, our LSTM-R capitalizes on a newly-devised relation-aware pointer network to select OCR tokens from the scene text for OCR-based image captioning.
SalientSleepNet: Multimodal Salient Wave Detection Network for Sleep Staging
Besides, the multimodal attention module is proposed to adaptively capture valuable information from multimodal data for the specific sleep stage.
Generalization Error Bound for Hyperbolic Ordinal Embedding
Hyperbolic ordinal embedding (HOE) represents entities as points in hyperbolic space so that they agree as well as possible with given constraints in the form of entity i is more similar to entity j than to entity k. It has been experimentally shown that HOE can obtain representations of hierarchical data such as a knowledge base and a citation network effectively, owing to hyperbolic space's exponential growth property.
Intentional Deep Overfit Learning (IDOL): A Novel Deep Learning Strategy for Adaptive Radiation Therapy
Finally, in the sCT reconstruction task, the MAE is reduced from 68 to 22 HU by utilizing the IDOL framework.
Prediction of Prognosis and Survival of Patients with Gastric Cancer by Weighted Improved Random Forest Model
Among the 10 public datasets, the Random Forest weighted in accuracy has the best performance on 6 datasets, with an average increase of 1. 44% in accuracy and an average increase of 1. 2% in AUC.
Scene Text Retrieval via Joint Text Detection and Similarity Learning
Such a task is usually realized by matching a query text to the recognized words, outputted by an end-to-end scene text spotter.
Learning to Filter: Siamese Relation Network for Robust Tracking
RD performs in a meta-learning way to obtain a learning ability to filter the distractors from the background while RM aims to effectively integrate the proposed RD into the Siamese framework to generate accurate tracking result.
Deep Simultaneous Optimisation of Sampling and Reconstruction for Multi-contrast MRI
MRI images of the same subject in different contrasts contain shared information, such as the anatomical structure.
Universal Undersampled MRI Reconstruction
Simply mixing images from multiple anatomies for training a single network does not lead to an ideal universal model due to the statistical shift among datasets of various anatomies, the need to retrain from scratch on all datasets with the addition of a new dataset, and the difficulty in dealing with imbalanced sampling when the new dataset is further of a smaller size.
Hierarchical Image Compression Framework
In learning-based image compression approaches, compression models are based on variational autoencoder(VAE) framework and optimized by a rate-distortion objective function, which achieve better performance than hybrid codecs.
Silo discharge of mixtures of soft and rigid grains
We study the outflow dynamics and clogging phenomena of mixtures of soft, elastic low-friction spherical grains and hard frictional spheres of similar size in a quasi-two-dimensional (2D) silo with narrow orifice at the bottom.
Soft Condensed Matter
Uncertainty-Based Adaptive Learning for Reading Comprehension
Recent years have witnessed a surge of successful applications of machine reading comprehension.
A Guide to Global Quantum Key Distribution Networks
We describe systems and methods for the deployment of global quantum key distribution (QKD) networks covering transoceanic, long-haul, metro, and access segments of the network.
Quantum Physics Cryptography and Security Computers and Society Networking and Internet Architecture
The Hoffman program of graphs: old and new
The Hoffman program with respect to any real or complex square matrix $M$ associated to a graph $G$ stems from A. J. Hoffman's pioneering work on the limit points for the spectral radius of adjacency matrices of graphs less than $\sqrt{2+\sqrt{5}}$.
Combinatorics 05C50
SGB: Stochastic Gradient Bound Method for Optimizing Partition Functions
The update of the proposed method, that we refer to as Stochastic Partition Function Bound (SPFB), resembles scaled stochastic gradient descent where the scaling factor relies on a second order term that is however different from the Hessian.
Hot and counter-rotating star-forming disk galaxies in IllustrisTNG and their real-world counterparts
A key feature of a large population of low-mass, late-type disk galaxies are star-forming disks with exponential light distributions.
Astrophysics of Galaxies
Point Cloud Attribute Compression via Successive Subspace Graph Transform
Inspired by the recently proposed successive subspace learning (SSL) principles, we develop a successive subspace graph transform (SSGT) to address point cloud attribute compression in this work.
Fermion-fermion interaction driven instability and criticality of quadratic band crossing systems with the breaking of time-reversal symmetry
We carefully study how the fermion-fermion interactions affect the low-energy states of a two-dimensional spin-$1/2$ fermionic system on the kagom\'{e} lattice with a quadratic band crossing point.
Strongly Correlated Electrons Mesoscale and Nanoscale Physics
Eliminating the Barriers: Demystifying Wi-Fi Baseband Design and Introducing the PicoScenes Wi-Fi Sensing Platform
Three barriers always hamper the research: unknown baseband design and its influence, inadequate hardware, and the lack of versatile and flexible measurement software.
Hardware Architecture
Towards automatic visual inspection: A weakly supervised learning method for industrial applicable object detection
With the recent progress of deep learning, advanced industrial object detectors are built for smart industrial applications.
Ranked #28 on
Weakly Supervised Object Detection
on PASCAL VOC 2007
LogoDet-3K: A Large-Scale Image Dataset for Logo Detection
LogoDet-3K creates a more challenging benchmark for logo detection, for its higher comprehensive coverage and wider variety in both logo categories and annotated objects compared with existing datasets.
Ranked #1 on
Object Detection
on FlickrLogos-32
A Functional Model for Structure Learning and Parameter Estimation in Continuous Time Bayesian Network: An Application in Identifying Patterns of Multiple Chronic Conditions
Bayesian networks are powerful statistical models to study the probabilistic relationships among set random variables with major applications in disease modeling and prediction.
FaultFace: Deep Convolutional Generative Adversarial Network (DCGAN) based Ball-Bearing Failure Detection Method
From the obtained faceportraits, a Deep Convolutional Generative Adversarial Network is employed to produce new faceportraits of the nominal and failure behaviors to get a balanced dataset.
GraphSleepNet: Adaptive Spatial-Temporal Graph Convolutional Networks for Sleep Stage Classification
However, how to effectively utilize brain spatial features and transition information among sleep stages continues to be challenging.
Information-Based Model Discrimination for Digital Twin Behavioral Matching
Its search can be done using optimization-based techniques, producing a family of models based on different system datasets, so, a discrimination criterion is required to determine the best Digital Twin model.
Multi-Domain Named Entity Recognition with Genre-Aware and Agnostic Inference
Named entity recognition is a key component of many text processing pipelines and it is thus essential for this component to be robust to different types of input.
Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment
To solve this problem, we introduce a Gaussian-guided latent alignment approach to align the latent feature distributions of the two domains under the guidance of the prior distribution.
Ranked #1 on
Domain Adaptation
on SYNSIG-to-GTSRB
Generating Fundus Fluorescence Angiography Images from Structure Fundus Images Using Generative Adversarial Networks
Fluorescein angiography can provide a map of retinal vascular structure and function, which is commonly used in ophthalmology diagnosis, however, this imaging modality may pose risks of harm to the patients.
Dendrite Net with Acceleration Module for Faster Nonlinear Mapping and System Identification
Significance: DD with AC can be used for most engineering systems, such as sensor systems, and will speed up computation in these online systems.
AGE Challenge: Angle Closure Glaucoma Evaluation in Anterior Segment Optical Coherence Tomography
To address this, we organized the Angle closure Glaucoma Evaluation challenge (AGE), held in conjunction with MICCAI 2019.
A Relation Spectrum Inheriting Taylor Series: Muscle Synergy and Coupling for Hand
However, this link has yet to be understood due to the complexity of human hand.
Dendrite Net: A White-Box Module for Classification, Regression, and System Identification
The main contribution of this paper is the basic machine learning algorithm (DD) with a white-box attribute, controllable precision for better generalization capability, and lower computational complexity.
Defect segmentation: Mapping tunnel lining internal defects with ground penetrating radar data using a convolutional neural network
This research proposes a Ground Penetrating Radar (GPR) data processing method for non-destructive detection of tunnel lining internal defects, called defect segmentation.
Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation
With the development of deep learning techniques, the combination of deep learning with image compression has drawn lots of attention.
Data Efficient Training for Reinforcement Learning with Adaptive Behavior Policy Sharing
Deep Reinforcement Learning (RL) is proven powerful for decision making in simulated environments.
Learning Hyperspectral Feature Extraction and Classification with ResNeXt Network
The Hyperspectral image (HSI) classification is a standard remote sensing task, in which each image pixel is given a label indicating the physical land-cover on the earth's surface.
Domain adaptation model for retinopathy detection from cross-domain OCT images
A deep neural network (DNN) can assist in retinopathy screening by automatically classifying patients into normal and abnormal categories according to optical coherence tomography (OCT) images.
Surface Following using Deep Reinforcement Learning and a GelSightTactile Sensor
Tactile sensors can provide detailed contact in-formation that can facilitate robots to perform dexterous, in-hand manipulation tasks.
Robotics
Logo-2K+: A Large-Scale Logo Dataset for Scalable Logo Classification
Moreover, we propose a Discriminative Region Navigation and Augmentation Network (DRNA-Net), which is capable of discovering more informative logo regions and augmenting these image regions for logo classification.
Enabling Highly Efficient Capsule Networks Processing Through A PIM-Based Architecture Design
In recent years, the CNNs have achieved great successes in the image processing tasks, e. g., image recognition and object detection.
RecSim: A Configurable Simulation Platform for Recommender Systems
We propose RecSim, a configurable platform for authoring simulation environments for recommender systems (RSs) that naturally supports sequential interaction with users.
Knowledge Consistency between Neural Networks and Beyond
As a generic tool, our method can be broadly used for different applications.
Convolutional Auto-encoding of Sentence Topics for Image Paragraph Generation
A valid question is how to encapsulate such gists/topics that are worthy of mention from an image, and then describe the image from one topic to another but holistically with a coherent structure.
Structure fusion based on graph convolutional networks for semi-supervised classification
By solving this function, we can simultaneously obtain the fusion spectral embedding from the multi-view data and the fusion structure as adjacent matrix to input graph convolutional networks for semi-supervised classification.
Ranked #31 on
Node Classification
on Citeseer
Reinforcement Learning for Slate-based Recommender Systems: A Tractable Decomposition and Practical Methodology
(i) We develop SLATEQ, a decomposition of value-based temporal-difference and Q-learning that renders RL tractable with slates.
Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features
Learning on point cloud is eagerly in demand because the point cloud is a common type of geometric data and can aid robots to understand environments robustly.
Combining many-objective radiomics and 3D convolutional neural network through evidential reasoning to predict lymph node metastasis in head and neck cancer
The hybrid method provides a more accurate way for predicting LNM using PET and CT.
Directional PointNet: 3D Environmental Classification for Wearable Robotics
Environmental information can provide reliable prior information about human motion intent, which can aid the subject with wearable robotics to walk in complex environments.
Unsupervised Domain Adaptation Learning Algorithm for RGB-D Staircase Recognition
However, the performance of traditional ML techniques is limited by the amount of labeled RGB-D staircase data.
Generating Synthesized Computed Tomography (CT) from Cone-Beam Computed Tomography (CBCT) using CycleGAN for Adaptive Radiation Therapy
Dose calculation accuracy using sCT images has been improved over the original CBCT images, with the average Gamma Index passing rate increased from 95. 4% to 97. 4% for 1 mm/1% criteria.
Medical Physics
Predicting Lung Nodule Malignancies by Combining Deep Convolutional Neural Network and Handcrafted Features
The fusion algorithm takes full advantage of the handcrafted features and the highest level CNN features learned at the output layer.
Towards Mitigating the Class-Imbalance Problem for Partial Label Learning
Partial label (PL) learning aims to induce a multi-class classifier from training examples where each of them is associated with a set of candidate labels, among which only one is valid.
