Search Results for author:
Found 84 papers, 24 papers with code
MA-SAM: Modality-agnostic SAM Adaptation for 3D Medical Image Segmentation
The Segment Anything Model (SAM), a foundation model for general image segmentation, has demonstrated impressive zero-shot performance across numerous natural image segmentation tasks.
Selection of contributing factors for predicting landslide susceptibility using machine learning and deep learning models
In this study, the impact of the selection of contributing factors on the accuracy of landslide susceptibility predictions using ML and DL models was investigated.
Radiology-Llama2: Best-in-Class Large Language Model for Radiology
This paper introduces Radiology-Llama2, a large language model specialized for radiology through a process known as instruction tuning.
Treatment Outcome Prediction for Intracerebral Hemorrhage via Generative Prognostic Model with Imaging and Tabular Data
Specifically, we propose to employ a variational autoencoder model to generate a low-dimensional prognostic score, which can effectively address the selection bias resulting from the non-randomized controlled trials.
Semantic Contrastive Bootstrapping for Single-positive Multi-label Recognition
Learning multi-label image recognition with incomplete annotation is gaining popularity due to its superior performance and significant labor savings when compared to training with fully labeled datasets.
Monte Carlo Policy Gradient Method for Binary Optimization
Binary optimization has a wide range of applications in combinatorial optimization problems such as MaxCut, MIMO detection, and MaxSAT.
REAL: A Representative Error-Driven Approach for Active Learning
Given a limited labeling budget, active learning (AL) aims to sample the most informative instances from an unlabeled pool to acquire labels for subsequent model training.
Radiology-GPT: A Large Language Model for Radiology
We introduce Radiology-GPT, a large language model for radiology.
Harmonic enhancement using learnable comb filter for light-weight full-band speech enhancement model
With fewer feature dimensions, filter banks are often used in light-weight full-band speech enhancement models.
AI Coach Assist: An Automated Approach for Call Recommendation in Contact Centers for Agent Coaching
In recent years, the utilization of Artificial Intelligence (AI) in the contact center industry is on the rise.
FedMR: Federated Learning via Model Recombination
Although Federated Learning (FL) enables global model training across clients without compromising their raw data, existing Federated Averaging (FedAvg)-based methods suffer from the problem of low inference performance, especially for unevenly distributed data among clients.
Trans-Inpainter: Wireless Channel Information- Guided Image Restoration via Multimodal Transformer
Image inpainting is a critical computer vision task to restore missing or damaged image regions.
Adversary-Aware Partial label learning with Label distillation
However, conventional partial-label learning (PLL) methods are still vulnerable to the high ratio of noisy partial labels, especially in a large labelling space.
HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining
Specifically, we propose a \textbf{HumanBench} based on existing datasets to comprehensively evaluate on the common ground the generalization abilities of different pretraining methods on 19 datasets from 6 diverse downstream tasks, including person ReID, pose estimation, human parsing, pedestrian attribute recognition, pedestrian detection, and crowd counting.
Ranked #1 on
Pedestrian Attribute Recognition
on PA-100K
Personalized speech enhancement combining band-split RNN and speaker attentive module
Target speaker information can be utilized in speech enhancement (SE) models to more effectively extract the desired speech.
Diffusion Model based Semi-supervised Learning on Brain Hemorrhage Images for Efficient Midline Shift Quantification
Brain midline shift (MLS) is one of the most critical factors to be considered for clinical diagnosis and treatment decision-making for intracranial hemorrhage.
Improving Named Entity Recognition in Telephone Conversations via Effective Active Learning with Human in the Loop
Telephone transcription data can be very noisy due to speech recognition errors, disfluencies, etc.
Multi-rate adaptive transform coding for video compression
Contemporary lossy image and video coding standards rely on transform coding, the process through which pixels are mapped to an alternative representation to facilitate efficient data compression.
Entity-level Sentiment Analysis in Contact Center Telephone Conversations
Entity-level sentiment analysis predicts the sentiment about entities mentioned in a given text.
An Effective, Performant Named Entity Recognition System for Noisy Business Telephone Conversation Transcripts
We present a simple yet effective method to train a named entity recognition (NER) model that operates on business telephone conversation transcripts that contain noise due to the nature of spoken conversation and artifacts of automatic speech recognition.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Spatial and Wavelength Division Joint Multiplexing System Design for Visible Light Communications
Instead of providing a new precoder/post-detector design, we investigate the considered joint multiplexing system from a system configuration perspective by tuning system parameters in both spatial and wavelength domains, such as LED positions and optical filter passband.
A Unified Two-Stage Group Semantics Propagation and Contrastive Learning Network for Co-Saliency Detection
With the design of negative samples, the noise objects are suppressed.
Online Active Regression
Active regression considers a linear regression problem where the learner receives a large number of data points but can only observe a small number of labels.
Simultaneously Learning Stochastic and Adversarial Bandits under the Position-Based Model
This work studies the OLTR problem in both stochastic and adversarial environments under the position-based model (PBM).
Contrastive Cross-Modal Knowledge Sharing Pre-training for Vision-Language Representation Learning and Retrieval
Concretely, the first module is a weight-sharing transformer that builds on the head of the visual and textual encoders, aiming to semantically align text and image.
Test-time Adaptation with Calibration of Medical Image Classification Nets for Label Distribution Shift
In this paper, we propose the first method to tackle label shift for medical image classification, which effectively adapt the model learned from a single training label distribution to arbitrary unknown test label distribution.
Online Reflective Learning for Robust Medical Image Segmentation
Deep segmentation models often face the failure risks when the testing image presents unseen distributions.
Single-domain Generalization in Medical Image Segmentation via Test-time Adaptation from Shape Dictionary
Domain generalization typically requires data from multiple source domains for model learning.
3D-model ShapeNet Core Classification using Meta-Semantic Learning
Understanding 3D point cloud models for learning purposes has become an imperative challenge for real-world identification such as autonomous driving systems.
DLTTA: Dynamic Learning Rate for Test-time Adaptation on Cross-domain Medical Images
Based on this estimated discrepancy, a dynamic learning rate adjustment strategy is then developed to achieve a suitable degree of adaptation for each test sample.
Histopathological Image Classification
Image Classification
+1
Developing a Production System for Purpose of Call Detection in Business Phone Conversations
In this paper we describe our implementation of a commercial system to detect Purpose of Call statements in English business call transcripts in real time.
BLINK with Elasticsearch for Efficient Entity Linking in Business Conversations
An Entity Linking system aligns the textual mentions of entities in a text to their corresponding entries in a knowledge base.
UTC: A Unified Transformer with Inter-Task Contrastive Learning for Visual Dialog
In this paper, we propose a contrastive learning-based framework UTC to unify and facilitate both discriminative and generative tasks in visual dialog with a single model.
Federated Learning Enables Big Data for Rare Cancer Boundary Detection
Although machine learning (ML) has shown promise in numerous domains, there are concerns about generalizability to out-of-sample data.
Inverse is Better! Fast and Accurate Prompt for Few-shot Slot Tagging
Such inverse prompting only requires a one-turn prediction for each slot type and greatly speeds up the prediction.
Exploring Intra- and Inter-Video Relation for Surgical Semantic Scene Segmentation
Automatic surgical scene segmentation is fundamental for facilitating cognitive intelligence in the modern operating theatre.
SHREC 2021: Classification in cryo-electron tomograms
To promote innovation in computational methods, we generate a novel simulated dataset to benchmark different methods of localization and classification of biological macromolecules in tomograms.
Impression Allocation and Policy Search in Display Advertising
In order to address the unstable traffic pattern challenge and achieve the optimal overall outcome, we propose a multi-agent reinforcement learning method to adjust the bids from each guaranteed contract, which is simple, converging efficiently and scalable.
A Unified Framework for Campaign Performance Forecasting in Online Display Advertising
Advertisers usually enjoy the flexibility to choose criteria like target audience, geographic area and bid price when planning an campaign for online display advertising, while they lack forecast information on campaign performance to optimize delivery strategies in advance, resulting in a waste of labour and budget for feedback adjustments.
Deep Single Image Deraining using An Asymetric Cycle Generative and Adversarial Framework
The former consists of parallel rain removal path and rain-fog feature extraction path by the rain and derain-fog network and the attention rain-fog feature extraction network (ARFE) , while the latter only contains a synthetic rain transformation path.
Unpaired Quad-Path Cycle Consistent Adversarial Networks for Single Image Defogging
To address these issues, we develop a novel generative adversarial network, called quad-path cycle consistent adversarial network (QPC-Net), for single image defogging.
MuZero with Self-competition for Rate Control in VP9 Video Compression
Specifically, we target the problem of learning a rate control policy to select the quantization parameters (QP) in the encoding process of libvpx, an open source VP9 video compression library widely used by popular video-on-demand (VOD) services.
Prediction of liquid fuel properties using machine learning models with Gaussian processes and probabilistic conditional generative learning
Accurate determination of fuel properties of complex mixtures over a wide range of pressure and temperature conditions is essential to utilizing alternative fuels.
bert2BERT: Towards Reusable Pretrained Language Models
However, large language model pre-training costs intensive computational resources and most of the models are trained from scratch without reusing the existing pre-trained models, which is wasteful.
Finding Second-Order Stationary Points in Nonconvex-Strongly-Concave Minimax Optimization
In this paper, we propose a novel approach for minimax optimization, called Minimax Cubic Newton (MCN), which could find an $\big(\varepsilon,\kappa^{1. 5}\sqrt{\rho\varepsilon}\,\big)$-second-order stationary point of $P({\bf x})$ with calling ${\mathcal O}\big(\kappa^{1. 5}\sqrt{\rho}\varepsilon^{-1. 5}\big)$ times of second-order oracles and $\tilde{\mathcal O}\big(\kappa^{2}\sqrt{\rho}\varepsilon^{-1. 5}\big)$ times of first-order oracles, where $\kappa$ is the condition number and $\rho$ is the Lipschitz continuous constant for the Hessian of $f({\bf x},{\bf y})$.
Improving Punctuation Restoration for Speech Transcripts via External Data
To leverage the available written text datasets, we introduce a data sampling technique based on an n-gram language model to sample more training data that are similar to our in-domain data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Assisted Learning for Organizations with Limited Imbalanced Data
We develop an assisted learning framework for assisting organization-level learners to improve their learning performance with limited and imbalanced data.
Assisted Learning for Organizations with Limited Data
We develop an assisted learning framework for assisting organization-level learners to improve their learning performance with limited and imbalanced data.
Source-Free Domain Adaptive Fundus Image Segmentation with Denoised Pseudo-Labeling
We present a novel denoised pseudo-labeling method for this problem, which effectively makes use of the source model and unlabeled target data to promote model self-adaptation from pseudo labels.
Efficient Combinatorial Optimization for Word-level Adversarial Textual Attack
Over the past few years, various word-level textual attack approaches have been proposed to reveal the vulnerability of deep neural networks used in natural language processing.
AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models
Specifically, we carefully design the techniques of one-shot learning and the search space to provide an adaptive and efficient development way of tiny PLMs for various latency constraints.
Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling
However, dialogue language understanding contains two closely related tasks, i. e., intent detection and slot filling, and often benefits from jointly learning the two tasks.
Extract then Distill: Efficient and Effective Task-Agnostic BERT Distillation
Task-agnostic knowledge distillation, a teacher-student framework, has been proved effective for BERT compression.
Certifiably-Robust Federated Adversarial Learning via Randomized Smoothing
Federated learning is an emerging data-private distributed learning framework, which, however, is vulnerable to adversarial attacks.
Temporal Memory Relation Network for Workflow Recognition from Surgical Video
In this paper, we propose a novel end-to-end temporal memory relation network (TMRNet) for relating long-range and multi-scale temporal patterns to augment the present features.
FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space
Federated learning allows distributed medical institutions to collaboratively learn a shared prediction model with privacy protection.
Computation Resource Allocation Solution in Recommender Systems
On the other hand, the response time of these systems is strictly limited to a short period, e. g. 300 milliseconds in our real system, which is also being exhausted by the increasingly complex models and algorithms.
MITNet: GAN Enhanced Magnetic Induction Tomography Based on Complex CNN
Magnetic induction tomography (MIT) is an efficient solution for long-term brain disease monitoring, which focuses on reconstructing bio-impedance distribution inside the human brain using non-intrusive electromagnetic fields.
C2C-GenDA: Cluster-to-Cluster Generation for Data Augmentation of Slot Filling
Slot filling, a fundamental module of spoken language understanding, often suffers from insufficient quantity and diversity of training data.
Neural Rate Control for Video Encoding using Imitation Learning
In modern video encoders, rate control is a critical component and has been heavily engineered.
Neural Network Training Techniques Regularize Optimization Trajectory: An Empirical Study
Specifically, we find that the optimization trajectories of successful DNN trainings consistently obey a certain regularity principle that regularizes the model update direction to be aligned with the trajectory direction.
Efficient Projection-Free Algorithms for Saddle Point Problems
The Frank-Wolfe algorithm is a classic method for constrained optimization problems.
Data Augmentation at the LHC through Analysis-specific Fast Simulation with Deep Learning
We present a fast simulation application based on a Deep Neural Network, designed to create large analysis-specific datasets.
FedCluster: Boosting the Convergence of Federated Learning via Cluster-Cycling
We develop FedCluster--a novel federated learning framework with improved optimization efficiency, and investigate its theoretical convergence properties.
FewJoint: A Few-shot Learning Benchmark for Joint Language Understanding
In this paper, we present FewJoint, a novel Few-Shot Learning benchmark for NLP.
Revisiting Co-Occurring Directions: Sharper Analysis and Efficient Algorithm for Sparse Matrices
We study the streaming model for approximate matrix multiplication (AMM).
Learning Directional Feature Maps for Cardiac MRI Segmentation
Cardiac MRI segmentation plays a crucial role in clinical diagnosis for evaluating personalized cardiac performance parameters.
Large-Scale Optimal Transport via Adversarial Training with Cycle-Consistency
Recent advances in large-scale optimal transport have greatly extended its application scenarios in machine learning.
Robust Multimodal Brain Tumor Segmentation via Feature Disentanglement and Gated Fusion
We tackle this challenge and propose a novel multimodal segmentation framework which is robust to the absence of imaging modalities.
Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentation
In this work, we present a novel unsupervised domain adaptation framework, named as Synergistic Image and Feature Alignment (SIFA), to effectively adapt a segmentation network to an unlabeled target domain.
An Optimization Principle Of Deep Learning?
In particular, we observe that the trainings that apply the training techniques achieve accelerated convergence and obey the principle with a large $\gamma$, which is consistent with the $\mathcal{O}(1/\gamma K)$ convergence rate result under the optimization principle.
A Stochastic Proximal Point Algorithm for Saddle-Point Problems
We consider saddle point problems which objective functions are the average of $n$ strongly convex-concave individual components.
Multi-Instance Multi-Scale CNN for Medical Image Classification
Deep learning for medical image classification faces three major challenges: 1) the number of annotated medical images for training are usually small; 2) regions of interest (ROIs) are relatively small with unclear boundaries in the whole medical images, and may appear in arbitrary positions across the x, y (and also z in 3D images) dimensions.
Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation
Our proposed SIFA is an elegant learning diagram which presents synergistic fusion of adaptations from both image and feature perspectives.
PnP-AdaNet: Plug-and-Play Adversarial Domain Adaptation Network with a Benchmark at Cross-modality Cardiac Segmentation
In this paper, we propose the PnPAdaNet (plug-and-play adversarial domain adaptation network) for adapting segmentation networks between different modalities of medical images, e. g., MRI and CT. We propose to tackle the significant domain shift by aligning the feature spaces of source and target domains in an unsupervised manner.
A Multi-Agent Reinforcement Learning Method for Impression Allocation in Online Display Advertising
With this formulation, we derive the optimal impression allocation strategy by solving the optimal bidding functions for contracts.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Semantic-Aware Generative Adversarial Nets for Unsupervised Domain Adaptation in Chest X-ray Segmentation
In spite of the compelling achievements that deep neural networks (DNNs) have made in medical image computing, these deep models often suffer from degraded performance when being applied to new test datasets with domain shift.
RPC Considered Harmful: Fast Distributed Deep Learning on RDMA
Its computation is typically characterized by a simple tensor data abstraction to model multi-dimensional matrices, a data-flow graph to model computation, and iterative executions with relatively frequent synchronizations, thereby making it substantially different from Map/Reduce style distributed big data computation.
Unsupervised Cross-Modality Domain Adaptation of ConvNets for Biomedical Image Segmentations with Adversarial Loss
The domain adaptation is more significant while challenging in the field of biomedical image analysis, where cross-modality data have largely different distributions.
Robust Frequent Directions with Application in Online Learning
We also apply RFD to online learning and propose an effective hyperparameter-free online Newton algorithm.
A Novel Method to Study Bottom-up Visual Saliency and its Neural Mechanism
In this study, we propose a novel method to measure bottom-up saliency maps of natural images.
A Parallel algorithm for $\mathcal{X}$-Armed bandits
To deal with these large-scale data sets, we study a distributed setting of $\mathcal{X}$-armed bandits, where $m$ players collaborate to find the maximum of the unknown function.
NV-Tree: Reducing Consistency Cost for NVM-based Single Level Systems
Although the memory fence and CPU cacheline flush instructions can order memory writes to achieve data consistency, they introduce a significant overhead (more than 10X slower in performance).
Regret vs. Communication: Distributed Stochastic Multi-Armed Bandits and Beyond
When the time horizon is unknown, we measure the frequency of communication through a new notion called the density of the communication set, and give an exact characterization of the interplay between regret and communication.
