Search Results for author:
Found 71 papers, 24 papers with code
Few-shot Named Entity Recognition via Superposition Concept Discrimination
Then a superposition instance retriever is applied to retrieve corresponding instances of these superposition concepts from large-scale text corpus.
A Semantic Search Engine for Mathlib4
In this paper, we present a semantic search engine for mathlib4 that accepts informal queries and finds the relevant theorems.
Meta-DSP: A Meta-Learning Approach for Data-Driven Nonlinear Compensation in High-Speed Optical Fiber Systems
Non-linear effects in long-haul, high-speed optical fiber systems significantly hinder channel capacity.
Large Language Models Illuminate a Progressive Pathway to Artificial Healthcare Assistant: A Review
This has sparked significant interest in applying LLMs to enhance various aspects of healthcare, ranging from medical education to clinical decision support.
Prompt Engineering Through the Lens of Optimal Control
In this paper, we propose an optimal control framework tailored for multi-round interactions with LLMs.
Latent assimilation with implicit neural representations for unknown dynamics
Data assimilation is crucial in a wide range of applications, but it often faces challenges such as high computational costs due to data dimensionality and incomplete understanding of underlying mechanisms.
Machine learning assisted exploration for affine Deligne-Lusztig varieties
We demonstrate that this framework has a potential to accelerate pure mathematical research, leading to the discovery of new conjectures and promising research directions that could otherwise take significant time to uncover.
Improved Prognostic Prediction of Pancreatic Cancer Using Multi-Phase CT by Integrating Neural Distance and Texture-Aware Transformer
Pancreatic ductal adenocarcinoma (PDAC) is a highly lethal cancer in which the tumor-vascular involvement greatly affects the resectability and, thus, overall survival of patients.
Learning to simulate partially known spatio-temporal dynamics with trainable difference operators
Recently, using neural networks to simulate spatio-temporal dynamics has received a lot of attention.
Cluster-Induced Mask Transformers for Effective Opportunistic Gastric Cancer Screening on Non-contrast CT Scans
In our experiments, the proposed method achieves a sensitivity of 85. 0% and specificity of 92. 6% for detecting gastric tumors on a hold-out test set consisting of 100 patients with cancer and 148 normal.
propnet: Propagating 2D Annotation to 3D Segmentation for Gastric Tumors on CT Scans
This model consists of a proposing stage for coarse segmentation and a refining stage for improved segmentation, using two-way branches for enhanced performance and an up-down strategy for efficiency.
Double Descent of Discrepancy: A Task-, Data-, and Model-Agnostic Phenomenon
In this paper, we studied two identically-trained neural networks (i. e. networks with the same architecture, trained on the same dataset using the same algorithm, but with different initialization) and found that their outputs discrepancy on the training dataset exhibits a "double descent" phenomenon.
Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Models
Memory is one of the most essential cognitive functions serving as a repository of world knowledge and episodes of activities.
Devil is in the Queries: Advancing Mask Transformers for Real-world Medical Image Segmentation and Out-of-Distribution Localization
Real-world medical image segmentation has tremendous long-tailed complexity of objects, among which tail conditions correlate with relatively rare diseases and are clinically significant.
ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models
(4) Can ChatGPT effectively leverage commonsense for answering questions?
A Comparative Study of Deep Learning and Iterative Algorithms for Joint Channel Estimation and Signal Detection
Joint channel estimation and signal detection (JCESD) in wireless communication systems is a crucial and challenging task, especially since it inherently poses a nonlinear inverse problem.
EDMAE: An Efficient Decoupled Masked Autoencoder for Standard View Identification in Pediatric Echocardiography
The EDMAE encoder is composed of a teacher and a student encoder.
Diffusion Model for Generative Image Denoising
In supervised learning for image denoising, usually the paired clean images and noisy images are collected or synthesised to train a denoising model.
L2SR: Learning to Sample and Reconstruct for Accelerated MRI via Reinforcement Learning
In this paper, we propose an alternating training framework for jointly learning a good pair of samplers and reconstructors via deep reinforcement learning (RL).
A Universal PINNs Method for Solving Partial Differential Equations with a Point Source
In recent years, deep learning technology has been used to solve partial differential equations (PDEs), among which the physics-informed neural networks (PINNs)method emerges to be a promising method for solving both forward and inverse PDE problems.
Region-Aware Metric Learning for Open World Semantic Segmentation via Meta-Channel Aggregation
Therefore, we propose a method called region-aware metric learning (RAML), which first separates the regions of the images and generates region-aware features for further metric learning.
A scalable deep learning approach for solving high-dimensional dynamic optimal transport
In this work, we propose a deep learning based method to solve the dynamic optimal transport in high dimensional space.
From 2D Images to 3D Model:Weakly Supervised Multi-View Face Reconstruction with Deep Fusion
While weakly supervised multi-view face reconstruction (MVR) is garnering increased attention, one critical issue still remains open: how to effectively fuse multiple image information to reconstruct high-precision 3D models.
A Note on Machine Learning Approach for Computational Imaging
Computational imaging has been playing a vital role in the development of natural sciences.
Trained Model in Supervised Deep Learning is a Conditional Risk Minimizer
We proved that a trained model in supervised deep learning minimizes the conditional risk for each input (Theorem 2. 1).
Layer-Parallel Training of Residual Networks with Auxiliary-Variable Networks
Gradient-based methods for the distributed training of residual networks (ResNets) typically require a forward pass of the input data, followed by back-propagating the error gradient to update model parameters, which becomes time-consuming as the network goes deeper.
Implicit Feature Refinement for Instance Segmentation
Our IFR enjoys several advantages: 1) simulates an infinite-depth refinement network while only requiring parameters of single residual block; 2) produces high-level equilibrium instance features of global receptive field; 3) serves as a plug-and-play general module easily extended to most object recognition frameworks.
Meta-Auto-Decoder for Solving Parametric Partial Differential Equations
Many important problems in science and engineering require solving the so-called parametric partial differential equations (PDEs), i. e., PDEs with different physical parameters, boundary conditions, shapes of computation domains, etc.
Solving Partial Differential Equations with Point Source Based on Physics-Informed Neural Networks
In recent years, deep learning technology has been used to solve partial differential equations (PDEs), among which the physics-informed neural networks (PINNs) emerges to be a promising method for solving both forward and inverse PDE problems.
Unsupervised Domain Adaptation in Semantic Segmentation Based on Pixel Alignment and Self-Training
This paper proposes an unsupervised cross-modality domain adaptation approach based on pixel alignment and self-training.
Layer-Parallel Training of Residual Networks with Auxiliary Variables
Backpropagation algorithm is indispensable for training modern residual networks (ResNets) and usually tends to be time-consuming due to its inherent algorithmic lockings.
VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results
Crowd counting on the drone platform is an interesting topic in computer vision, which brings new challenges such as small object inference, background clutter and wide viewpoint.
SOLQ: Segmenting Objects by Learning Queries
Moreover, the joint learning of unified query representation can greatly improve the detection performance of DETR.
Ranked #4 on
Object Detection
on COCO minival
(AP75 metric)
MOTR: End-to-End Multiple-Object Tracking with Transformer
Temporal modeling of objects is a key challenge in multiple object tracking (MOT).
Ranked #1 on
Multi-Object Tracking
on MOT17
(e2e-MOT metric)
Multi-Object Tracking
Multiple Object Tracking with Transformer
+1
Improving Generalizability in Limited-Angle CT Reconstruction with Sinogram Extrapolation
More importantly, we show that using such a sinogram extrapolation module significantly improves the generalization capability of the model on unseen datasets (e. g., COVID-19 and LIDC datasets) when compared to existing approaches.
Feature Space Singularity for Out-of-Distribution Detection
Our analysis of the phenomenon reveals why our algorithm works.
Ranked #1 on
Out-of-Distribution Detection
on MS-1M vs. IJB-C
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Deep Interactive Denoiser (DID) for X-Ray Computed Tomography
However, there exists two challenges regarding the DL-based denoisers: 1) a trained model typically does not generate different image candidates with different noise-resolution tradeoffs which sometimes are needed for different clinical tasks; 2) the model generalizability might be an issue when the noise level in the testing images is different from that in the training dataset.
Enhancing Certified Robustness of Smoothed Classifiers via Weighted Model Ensembling
Moreover, SWEEN models constructed using a few small models can achieve comparable performance to a single large model with a notable reduction in training time.
A Practical Layer-Parallel Training Algorithm for Residual Networks
Gradient-based algorithms for training ResNets typically require a forward pass of the input data, followed by back-propagating the objective gradient to update parameters, which are time-consuming for deep ResNets.
Transferred Discrepancy: Quantifying the Difference Between Representations
Our experiments show that TD can provide fine-grained information for varied downstream tasks, and for the models trained from different initializations, the learned features are not the same in terms of downstream-task predictions.
Learning to Scan: A Deep Reinforcement Learning Approach for Personalized Scanning in CT Imaging
It is more desirable to design a personalized scanning strategy for each subject to obtain better reconstruction result.
RODE-Net: Learning Ordinary Differential Equations with Randomness from Data
To train the RODE-Net, we first estimate the parameters of the unknown RODE using the symbolic networks \cite{long2019pde} by solving a set of deterministic inverse problems based on the measured data, and use a generative adversarial network (GAN) to estimate the true distribution of the RODE's parameters.
MetaInv-Net: Meta Inversion Network for Sparse View CT Image Reconstruction
Other components, such as image priors and hyperparameters, are kept as the original design.
Enhancing Certified Robustness via Smoothed Weighted Ensembling
Moreover, SWEEN models constructed using a few small models can achieve comparable performance to a single large model with a notable reduction in training time.
Blind Adversarial Training: Balance Accuracy and Robustness
The main idea of this approach is to use a cutoff-scale strategy to adaptively estimate a nonuniform budget to modify the AEs used in the training, ensuring that the strengths of the AEs are dynamically located in a reasonable range and ultimately improving the overall robustness of the AT model.
Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View.
In particular, how words in a sentence are abstracted into contexts by passing through the layers of the Transformer can be interpreted as approximating multiple particles' movement in the space using the Lie-Trotter splitting scheme and the Euler's method.
Gazetteer-Enhanced Attentive Neural Networks for Named Entity Recognition
Current region-based NER models only rely on fully-annotated training data to learn effective region encoder, which often face the training data bottleneck.
Supervised neural machine translation based on data augmentation and improved training \& inference process
This is the second time for SRCB to participate in WAT.
Distillation $\approx$ Early Stopping? Harvesting Dark Knowledge Utilizing Anisotropic Information Retrieval For Overparameterized Neural Network
Assuming that the teacher network is overparameterized, we argue that the teacher network is essentially harvesting dark knowledge from the data via early stopping.
Distillation $\approx$ Early Stopping? Harvesting Dark Knowledge Utilizing Anisotropic Information Retrieval For Overparameterized NN
Assuming that the teacher network is overparameterized, we argue that the teacher network is essentially harvesting dark knowledge from the data via early stopping.
Annotation-Free Cardiac Vessel Segmentation via Knowledge Transfer from Retinal Images
Segmenting coronary arteries is challenging, as classic unsupervised methods fail to produce satisfactory results and modern supervised learning (deep learning) requires manual annotation which is often time-consuming and can some time be infeasible.
A Review on Deep Learning in Medical Image Reconstruction
More recently, as more data and computation resources are made available, deep learning based models (or deep models) pushed data-driven modeling to the extreme where the models are mostly based on learning with minimal human designs.
Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View
In this paper, we provide a novel perspective towards understanding the architecture: we show that the Transformer can be mathematically interpreted as a numerical Ordinary Differential Equation (ODE) solver for a convection-diffusion equation in a multi-particle dynamic system.
NPTC-net: Narrow-Band Parallel Transport Convolutional Neural Network on Point Clouds
Designing appropriate convolution neural networks on manifold-structured point clouds can inherit and empower recent advances of CNNs to analyzing and processing point cloud data.
Learning to Discretize: Solving 1D Scalar Conservation Laws via Deep Reinforcement Learning
Conservation laws are considered to be fundamental laws of nature.
You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle
Adversarial training, typically formulated as a robust optimization problem, is an effective way of improving the robustness of deep networks.
CURE: Curvature Regularization For Missing Data Recovery
For that, we introduce a new regularization by combining the low dimension manifold regularization with a higher order Curvature Regularization, and we call this new regularization CURE for short.
JSR-Net: A Deep Network for Joint Spatial-Radon Domain CT Reconstruction from incomplete data
CT image reconstruction from incomplete data, such as sparse views and limited angle reconstruction, is an important and challenging problem in medical imaging.
PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
Numerical experiments show that the PDE-Net 2. 0 has the potential to uncover the hidden PDE of the observed dynamics, and predict the dynamical behavior for a relatively long time, even in a noisy environment.
Whole Brain Susceptibility Mapping Using Harmonic Incompatibility Removal
Quantitative susceptibility mapping (QSM) aims to visualize the three dimensional susceptibility distribution by solving the field-to-source inverse problem using the phase data in magnetic resonance signal.
Parallel Transport Convolution: A New Tool for Convolutional Neural Networks on Manifolds
PTC allows for the construction of compactly supported filters and is also robust to manifold deformations.
Dynamically Unfolding Recurrent Restorer: A Moving Endpoint Control Method for Image Restoration
In this paper, we propose a new control framework called the moving endpoint control to restore images corrupted by different degradation levels in one model.
Nostalgic Adam: Weighting more of the past gradients when designing the adaptive learning rate
NosAdam can be regarded as a fix to the non-convergence issue of Adam in alternative to the recent work of [Reddi et al., 2018].
End-to-End Abnormality Detection in Medical Imaging
To align the acquisition with the annotations made by radiologists in the image domain, a DNN was built as the unrolled version of iterative reconstruction algorithms to map the acquisitions to images, and followed by a 3D convolutional neural network (CNN) to detect the abnormality in the reconstructed images.
End-to-end Lung Nodule Detection in Computed Tomography
With 144 multi-slice fanbeam pro-jections, the proposed end-to-end detector could achieve comparable sensitivity with the reference detector, which was trained and applied on the fully-sampled image data.
Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations
We show that many effective networks, such as ResNet, PolyNet, FractalNet and RevNet, can be interpreted as different numerical discretizations of differential equations.
PDE-Net: Learning PDEs from Data
In this paper, we present an initial attempt to learn evolution PDEs from data.
An Edge Driven Wavelet Frame Model for Image Restoration
Wavelet frame systems are known to be effective in capturing singularities from noisy and degraded images.
Building a comprehensive syntactic and semantic corpus of Chinese clinical texts
Objective: To build a comprehensive corpus covering syntactic and semantic annotations of Chinese clinical texts with corresponding annotation guidelines and methods as well as to develop tools trained on the annotated corpus, which supplies baselines for research on Chinese texts in the clinical domain.
Image Restoration: A General Wavelet Frame Based Model and Its Asymptotic Analysis
In this paper, we introduce a generic wavelet frame based image restoration model, called the "general model", which includes most of the existing wavelet frame based models as special cases.
