Search Results for author:
Found 166 papers, 46 papers with code
Pixel-Level Hand Detection in Ego-centric Videos
Our analysis highlights the effectiveness of sparse features and the importance of modeling global illumination.
Transferring Landmark Annotations for Cross-Dataset Face Alignment
We show extensive results on combining various popular databases (LFW, AFLW, LFPW, HELEN) for improved cross-dataset and unseen data alignment.
Face alignment by coarse-to-fine shape searching
We present a novel face alignment framework based on coarse-to-fine shape searching.
Ranked #20 on
Face Alignment
on AFLW-19
Towards Arbitrary-View Face Alignment by Recommendation Trees
The unified framework seamlessly handles different viewpoints and landmark protocols, and it is trained by optimising directly on landmark locations, thus yielding superior results on arbitrary-view face alignment.
Unconstrained Face Alignment via Cascaded Compositional Learning
We present a practical approach to address the problem of unconstrained face alignment for a single image.
Ranked #19 on
Face Alignment
on AFLW-19
DeepGraph: Graph Structure Predicts Network Growth
Conventionally, a graph structure is represented using an adjacency matrix or a set of hand-crafted structural features.
DeepCas: an End-to-end Predictor of Information Cascades
While many believe that they are inherently unpredictable, recent work has shown that some key properties of information cascades, such as size, growth, and shape, can be predicted by a machine learning algorithm that combines many features.
Less is More: Learning Prominent and Diverse Topics for Data Summarization
With this reinforced random walk as a general process embedded in classical topic models, we obtain \textit{diverse topic models} that are able to extract the most prominent and diverse topics from data.
Deep Memory Networks for Attitude Identification
In this way, signals produced in target detection provide clues for polarity classification, and reversely, the predicted polarity provides feedback to the identification of targets.
Budgeted Batch Bayesian Optimization With Unknown Batch Sizes
Current batch BO approaches are restrictive in that they fix the number of evaluations per batch, and this can be wasteful when the number of specified evaluations is larger than the number of real maxima in the underlying acquisition function.
Residual Attention Network for Image Classification
In this work, we propose "Residual Attention Network", a convolutional neural network using attention mechanism which can incorporate with state-of-art feed forward network architecture in an end-to-end training fashion.
Ranked #635 on
Image Classification
on ImageNet
Regularizing Model Complexity and Label Structure for Multi-Label Text Classification
Multi-label text classifiers need to be carefully regularized to prevent the severe over-fitting in the high dimensional space, and also need to take into account label dependencies in order to make accurate predictions under uncertainty.
Merge or Not? Learning to Group Faces via Imitation Learning
Given a large number of unlabeled face images, face grouping aims at clustering the images into individual identities present in the data.
High Dimensional Bayesian Optimization with Elastic Gaussian Process
Bayesian optimization is an efficient way to optimize expensive black-box functions such as designing a new product with highest quality or hyperparameter tuning of a machine learning algorithm.
Quantifying Facial Age by Posterior of Age Comparisons
We introduce a novel approach for annotating large quantity of in-the-wild facial images with high-quality posterior age distribution as labels.
Ranked #7 on
Age Estimation
on MORPH Album2
(using extra training data)
On Early-stage Debunking Rumors on Twitter: Leveraging the Wisdom of Weak Learners
Recently a lot of progress has been made in rumor modeling and rumor detection for micro-blogging streams.
From which world is your graph?
Discovering statistical structure from links is a fundamental problem in the analysis of social networks.
From which world is your graph
This work focuses on unifying two of the most widely used link-formation models: the stochastic block model (SBM) and the small world (or latent space) model (SWM).
Find the Conversation Killers: a Predictive Study of Thread-ending Posts
In this study, we are particularly interested in identifying a post in a multi-party conversation that is unlikely to be further replied to, which therefore kills that thread of the conversation.
High Dimensional Bayesian Optimization Using Dropout
Scaling Bayesian optimization to high dimensions is challenging task as the global optimization of high-dimensional acquisition function can be expensive and often infeasible.
Covariance Function Pre-Training with m-Kernels for Accelerated Bayesian Optimisation
The paper presents a novel approach to direct covariance function learning for Bayesian optimisation, with particular emphasis on experimental design problems where an existing corpus of condensed knowledge is present.
Rapid Bayesian optimisation for synthesis of short polymer fiber materials
The discovery of processes for the synthesis of new materials involves many decisions about process design, operation, and material properties.
Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
However, many contemporary face recognition models still perform relatively poor in processing profile faces compared to frontal faces.
Ranked #1 on
Face Identification
on IJB-A
Accelerated Bayesian Optimization throughWeight-Prior Tuning
In this paper we show how such auxiliary data may be used to construct a GP covariance corresponding to a more appropriate weight prior for the objective function.
ReenactGAN: Learning to Reenact Faces via Boundary Transfer
A transformer is subsequently used to adapt the boundary of source face to the boundary of target face.
The Devil of Face Recognition is in the Noise
2) With the original datasets and cleaned subsets, we profile and analyze label noise properties of MegaFace and MS-Celeb-1M.
Matrix Factorization on GPUs with Memory Optimization and Approximate Computing
Current MF implementations are either optimized for a single machine or with a need of a large computer cluster but still are insufficient.
SCOPE: C3SR Systems Characterization and Benchmarking Framework
This report presents the design of the Scope infrastructure for extensible and portable benchmarking.
Performance
Classifying Mammographic Breast Density by Residual Learning
Mammographic breast density, a parameter used to describe the proportion of breast tissue fibrosis, is widely adopted as an evaluation characteristic of the likelihood of breast cancer incidence.
Unsupervised Disentangling Structure and Appearance
It is challenging to disentangle an object into two orthogonal spaces of structure and appearance since each can influence the visual observation in a different and unpredictable way.
AUNet: Attention-guided dense-upsampling networks for breast mass segmentation in whole mammograms
In AUNet, we employ an asymmetrical encoder-decoder structure and propose an effective upsampling block, attention-guided dense-upsampling block (AU block).
Practical Batch Bayesian Optimization for Less Expensive Functions
Bayesian optimization (BO) and its batch extensions are successful for optimizing expensive black-box functions.
TrIMS: Transparent and Isolated Model Sharing for Low Latency Deep LearningInference in Function as a Service Environments
Deep neural networks (DNNs) have become core computation components within low latency Function as a Service (FaaS) prediction pipelines: including image recognition, object detection, natural language processing, speech synthesis, and personalized recommendation pipelines.
Distributed, Parallel, and Cluster Computing
Frustrated with Replicating Claims of a Shared Model? A Solution
Machine Learning (ML) and Deep Learning (DL) innovations are being introduced at such a rapid pace that model owners and evaluators are hard-pressed analyzing and studying them.
TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank
We propose TensorFlow Ranking, the first open source library for solving large-scale ranking problems in a deep learning framework.
Anti-drift in electronic nose via dimensionality reduction: a discriminative subspace projection approach
In this paper, we propose a sensor drift correction method to deal with the sensor drift problem.
Adapting RNN Sequence Prediction Model to Multi-label Set Prediction
Previous such RNN models define probabilities for sequences but not for sets; attempts to obtain a set probability are after-thoughts of the network design, including pre-specifying the label order, or relating the sequence probability to the set probability in ad hoc ways.
Deep Comprehensive Correlation Mining for Image Clustering
Recent developed deep unsupervised methods allow us to jointly learn representation and cluster unlabelled data.
Ranked #7 on
Image Clustering
on Tiny-ImageNet
TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation
Extensive experiments demonstrate the superior performance of our method to other state-of-the-art approaches, especially in the challenging near-rigid and non-rigid objects translation tasks.
Challenges and Pitfalls of Machine Learning Evaluation and Benchmarking
An increasingly complex and diverse collection of Machine Learning (ML) models as well as hardware/software stacks, collectively referred to as "ML artifacts", are being proposed - leading to a diverse landscape of ML.
Disentangling Content and Style via Unsupervised Geometry Distillation
It is challenging to disentangle an object into two orthogonal spaces of content and style since each can influence the visual observation differently and unpredictably.
Evidence for $Z_{c}^{\pm}$ decays into the $ρ^{\pm} η_{c}$ final state
We study $e^{+}e^{-}$ collisions with a $\pi^{+}\pi^{-}\pi^{0}\eta_{c}$ final state using data samples collected with the BESIII detector at center-of-mass energies $\sqrt{s}=4. 226$, $4. 258$, $4. 358$, $4. 416$, and $4. 600$ GeV.
High Energy Physics - Experiment
Sparse Spectrum Gaussian Process for Bayesian Optimization
Since the balance between predictive mean and the predictive variance is the key determinant to the success of Bayesian optimization, the current sparse spectrum methods are less suitable for it.
X-Net: Brain Stroke Lesion Segmentation Based on Depthwise Separable Convolution and Long-range Dependencies
Recently, approaches based on deep learning and methods for contextual information extraction have served in many image segmentation tasks.
CLCI-Net: Cross-Level fusion and Context Inference Networks for Lesion Segmentation of Chronic Stroke
To address these challenges, this paper proposes a Cross-Level fusion and Context Inference Network (CLCI-Net) for the chronic stroke lesion segmentation from T1-weighted MR images.
Accelerating Experimental Design by Incorporating Experimenter Hunches
In this paper, we consider per-variable monotonic trend in the underlying property that results in a unimodal trend in those variables for a target value optimization.
One-shot Face Reenactment
However, in real-world scenario end-users often only have one target face at hand, rendering existing methods inapplicable.
Model-based Convolutional De-Aliasing Network Learning for Parallel MR Imaging
Three main contributions have been made: a de-aliasing reconstruction model was proposed to accelerate parallel MR imaging with deep learning exploring both spatial redundancy and multi-coil correlations; a split Bregman iteration algorithm was developed to solve the model efficiently; and unlike most existing parallel imaging methods which rely on the accuracy of the estimated multi-coil sensitivity, the proposed method can perform parallel reconstruction from undersampled data without explicit sensitivity calculation.
Learning Cross-Modal Deep Representations for Multi-Modal MR Image Segmentation
From the different modalities, one modality that contributes most to the results is selected as the master modality, which supervises the information selection of the other assistant modalities.
Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wild
Specifically, we focus on the challenging task of in-the-wild 3D human recovery from single images when paired 3D annotations are not fully available.
XSP: Across-Stack Profiling and Analysis of Machine Learning Models on GPUs
Such an endeavor is challenging as the characteristics of an ML model depend on the interplay between the model, framework, system libraries, and the hardware (or the HW/SW stack).
Interpretable Biomanufacturing Process Risk and Sensitivity Analyses for Quality-by-Design and Stability Control
While biomanufacturing plays a significant role in supporting the economy and ensuring public health, it faces critical challenges, including complexity, high variability, lengthy lead time, and very limited process data, especially for personalized new cell and gene biotherapeutics.
AI Matrix: A Deep Learning Benchmark for Alibaba Data Centers
Alibaba has China's largest e-commerce platform.
MLModelScope: A Distributed Platform for ML Model Evaluation and Benchmarking at Scale
Machine Learning (ML) and Deep Learning (DL) innovations are being introduced at such a rapid pace that researchers are hard-pressed to analyze and study them.
Self-Adaptive Network Pruning
Our method introduces a general Saliency-and-Pruning Module (SPM) for each convolutional layer, which learns to predict saliency scores and applies pruning for each channel.
Benanza: Automatic $μ$Benchmark Generation to Compute "Lower-bound" Latency and Inform Optimizations of Deep Learning Models on GPUs
An important venue for such improvement is to profile the execution of these models and characterize their performance to identify possible optimization opportunities.
DLBricks: Composable Benchmark Generation to Reduce Deep Learning Benchmarking Effort on CPUs (Extended)
We show that DLBricks provides an accurate performance estimate for the DL models and reduces the benchmarking time across systems (e. g. within $95\%$ accuracy and up to $4. 4\times$ benchmarking time speedup on Amazon EC2 c5. xlarge).
The Design and Implementation of a Scalable DL Benchmarking Platform
MLModelScope defines abstractions for frameworks and supports board range of DL models and evaluation scenarios.
Non-rigid Registration Method between 3D CT Liver Data and 2D Ultrasonic Images based on Demons Model
The non-rigid registration between CT data and ultrasonic images of liver can facilitate the diagnosis and treatment, which has been widely studied in recent years.
MLModelScope: A Distributed Platform for Model Evaluation and Benchmarking at Scale
Machine Learning (ML) and Deep Learning (DL) innovations are being introduced at such a rapid pace that researchers are hard-pressed to analyze and study them.
DLSpec: A Deep Learning Task Exchange Specification
Deep Learning (DL) innovations are being introduced at a rapid pace.
Incorporating Expert Prior Knowledge into Experimental Design via Posterior Sampling
Again, it is unknown how to incorporate the expert prior knowledge about the global optimum into Bayesian optimization process.
Relating the structure of dark matter halos to their assembly and environment
Using decision trees built with the random ensemble method, we find that the correlation between halo concentration and assembly history is tight: more than 60% of the variance in halo concentration can be explained by assembly history alone.
Astrophysics of Galaxies Cosmology and Nongalactic Astrophysics
Incorporating Expert Prior in Bayesian Optimisation via Space Warping
In this paper, we represent the prior knowledge about the function optimum through a prior distribution.
Downstream Model Design of Pre-trained Language Model for Relation Extraction Task
We believe that PLMs can also be used to solve the relation extraction problem, but it is necessary to establish a specially designed downstream task model or even loss function for dealing with complicated relations.
Ranked #3 on
Relation Extraction
on SemEval-2010 Task-8
Hierarchically Fair Federated Learning
When the federated learning is adopted among competitive agents with siloed datasets, agents are self-interested and participate only if they are fairly rewarded.
Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching
In order to better capture sentence level semantic relations within a document, we pre-train the model with a novel masked sentence block language modeling task in addition to the masked word language modeling task used by BERT.
Classification Trees for Imbalanced and Sparse Data: Surface-to-Volume Regularization
When data are limited in one or more of the classes, the estimated decision boundaries are often irregularly shaped due to the limited sample size, leading to poor generalization error.
Towards in-store multi-person tracking using head detection and track heatmaps
In addition, we describe an illustrative example of the use of this dataset for tracking participants based on a head tracking model in an effort to minimize errors due to occlusion.
A Complex KBQA System using Multiple Reasoning Paths
Multi-hop knowledge based question answering (KBQA) is a complex task for natural language understanding.
Model independent determination of the spin of the $Ω^{-}$ and its polarization alignment in $ψ(3686)\rightarrowΩ^{-}\barΩ^{+}$
We present an analysis of the process $\psi(3686) \to \Omega^- \bar{\Omega}^+$ ($\Omega^-\to K^-\Lambda$, $\bar{\Omega}^+\to K^+\bar{\Lambda}$, $\Lambda\to p\pi^-$, $\bar{\Lambda}\to \bar{p}\pi^+$) based on a data set of $448\times 10^6$ $\psi(3686)$ decays collected with the BESIII detector at the BEPCII electron-positron collider.
High Energy Physics - Experiment
A coarse-to-fine framework for unsupervised multi-contrast MR image deformable registration with dual consistency constraint
Multi-contrast magnetic resonance (MR) image registration is useful in the clinic to achieve fast and accurate imaging-based disease diagnosis and treatment planning.
Simultaneously-Collected Multimodal Lying Pose Dataset: Towards In-Bed Human Pose Monitoring under Adverse Vision Conditions
Computer vision (CV) has achieved great success in interpreting semantic meanings from images, yet CV algorithms can be brittle for tasks with adverse vision conditions and the ones suffering from data/label pair limitation.
Measuring galaxy abundance and clustering at high redshift from incomplete spectroscopic data: Tests on mock catalogs
We also quantify improvements expected in the PFS-like galaxy survey relative to zCOSMOS and VIPERS surveys.
Astrophysics of Galaxies
Leveraging Semantic and Lexical Matching to Improve the Recall of Document Retrieval Systems: A Hybrid Approach
A hybrid approach, which leverages both semantic (deep neural network-based) and lexical (keyword matching-based) retrieval models, is proposed.
PaGraph: Scaling GNN Training on Large Graphs via Computation-aware Caching and Partitioning
Emerging graph neural networks (GNNs) have extended the successes of deep learning techniques against datasets like images and texts to more complex graph-structured data.
Search for the reaction $e^{+}e^{-} \rightarrow π^{+}π^{-} χ_{cJ}$ and a charmonium-like structure decaying to $χ_{cJ}π^{\pm}$ between 4.18 and 4.60 GeV
We search for the process $e^{+}e^{-}\rightarrow \pi ^{+}\pi ^{-} \chi_{cJ}$ ($J=0, 1, 2$) and for a charged charmonium-like state in the $\pi ^{\pm} \chi_{cJ}$ subsystem.
High Energy Physics - Experiment
Annotation-efficient deep learning for automatic medical image segmentation
Automatic medical image segmentation plays a critical role in scientific research and medical care.
The water abundance in Jupiter's equatorial zone
Oxygen is the most common element after hydrogen and helium in Jupiter's atmosphere, and may have been the primary condensable (as water ice) in the protoplanetary disk.
Earth and Planetary Astrophysics
Storms and the Depletion of Ammonia in Jupiter: II. Explaining the Juno Observations
In parallel, the Equatorial Zone is peculiar for its absence of lightning, which is otherwise prevalent most everywhere else on the planet.
Earth and Planetary Astrophysics Solar and Stellar Astrophysics
Measurements of the center-of-mass energies of $e^{+}e^{-}$ collisions at BESIII
During the 2016-17 and 2018-19 running periods, the BESIII experiment collected 7. 5~fb$^{-1}$ of $e^+e^-$ collision data at center-of-mass energies ranging from 4. 13 to 4. 44 GeV.
High Energy Physics - Experiment
Robustness Testing of Language Understanding in Task-Oriented Dialog
Most language understanding models in task-oriented dialog systems are trained on a small amount of annotated training data, and evaluated in a small set from the same distribution.
Hyperspectral Image Denoising With Realistic Data
On the other hand, we propose an accurate HSI noise model which matches the distribution of real data well and can be employed to synthesize realistic dataset.
Cross section measurement of $e^+e^- \to p\bar{p}η$ and $e^+e^- \to p\bar{p}ω$ at center-of-mass energies between 3.773 GeV and 4.6 GeV
Based on $14. 7~\textrm{fb}^{-1}$ of $e^+e^-$ annihilation data collected with the BESIII detector at the BEPCII collider at 17 different center-of-mass energies between $3. 7730~\textrm{GeV}$ and $4. 5995~\textrm{GeV}$, Born cross sections of the two processes $e^+e^- \to p\bar{p}\eta$ and $e^+e^- \to p\bar{p}\omega$ are measured for the first time.
High Energy Physics - Experiment
Measurement of the absolute branching fractions for purely leptonic $D_s^+$ decays
Constraining our measurement to the Standard Model expectation of lepton universality ($R=9. 75$), we find the more precise results $\cal B(D_s^+\to \tau^+\nu_\tau) = (5. 22\pm0. 10\pm 0. 14)\times10^{-2}$ and $A_{\it CP}(\tau^\pm\nu_\tau) = (-0. 1\pm1. 9\pm1. 0)\%$.
High Energy Physics - Experiment
Efficient Multi-Stage Video Denoising with Recurrent Spatio-Temporal Fusion
Then, a denoising stage removes the noise in the fused frame.
Ranked #3 on
Video Denoising
on CRVD
Ion-beam-assisted characterization of quinoline-insoluble particles in nuclear graphite
A much higher concentration of QI particles in NBG-18 than IG-110 was characterized and is suggested to be responsible for the smaller maximum dimensional shrinkage of NBG-18 than IG-110 during irradiation.
Applied Physics
Supervised Learning in the Presence of Noise: Application in ICD-10 Code Classification
We first identify ICD-10 codes that human coders tend to misuse or confuse, based on the codes' locations in the ICD-10 hierarchy, the types of the codes, and baseline classifier's prediction behaviors; we then develop a novel training strategy that accounts for such noise.
LAMPRET: Layout-Aware Multimodal PreTraining for Document Understanding
text, table, image) and propose a novel layout-aware multimodal hierarchical framework, LAMPreT, to model the blocks and the whole document.
NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results.
Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report
A detailed description of all models developed in the challenge is provided in this paper.
Blind Image Quality Assessment for MRI with A Deep Three-dimensional content-adaptive Hyper-Network
However, the performance of these methods is limited due to the utilization of simple content-non-adaptive network parameters and the waste of the important 3D spatial information of the medical images.
VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection
Lane detection plays a key role in autonomous driving.
A Novel Hybrid Convolutional Neural Network for Accurate Organ Segmentation in 3D Head and Neck CT Images
An essential step of RT planning is the accurate segmentation of various organs-at-risks (OARs) in HaN CT images.
Group Shift Pointwise Convolution for Volumetric Medical Image Segmentation
Recent studies have witnessed the effectiveness of 3D convolutions on segmenting volumetric medical images.
Self-Supervised Learning for MRI Reconstruction with a Parallel Network Training Framework
Specifically, during model optimization, two subsets are constructed by randomly selecting part of k-space data from the undersampled data and then fed into two parallel reconstruction networks to perform information recovery.
Finding One Missing Puzzle of Contextual Word Embedding: Representing Contexts as Manifold
The current understanding of contextual word embedding interprets the representation by associating each token to a vector that is dynamically modulated by the context.
Demystifying Hyperparameter Optimization in Federated Learning
Such data heterogeneity and privacy requirements bring unique challenges for learning hyperparameter optimization as the training dynamics change across clients even within the same training round and they are difficult to measure due to privacy constraints.
Radiomic biomarker extracted from PI-RADS 3 patients support more eìcient and robust prostate cancer diagnosis: a multi-center study
Prostate Imaging Reporting and Data System (PI-RADS) based on multi-parametric MRI classi\^ees patients into 5 categories (PI-RADS 1-5) for routine clinical diagnosis guidance.
Expert Knowledge-guided Geometric Representation Learning for Magnetic Resonance Imaging-based Glioma Grading
Geometric manifolds of hand-crafted features and learned features are constructed to mine the implicit relationship between deep learning and radiomics, and therefore to dig mutual consent and essential representation for the glioma grades.
PARCEL: Physics-based Unsupervised Contrastive Representation Learning for Multi-coil MR Imaging
However, in the absence of high-quality, fully sampled datasets for training, the performance of these methods is limited.
Rethinking the optimization process for self-supervised model-driven MRI reconstruction
Recovering high-quality images from undersampled measurements is critical for accelerated MRI reconstruction.
SJ-HD^2R: Selective Joint High Dynamic Range and Denoising Imaging for Dynamic Scenes
To further leverage these two paradigms, we propose a selective and joint HDR and denoising (SJ-HD$^2$R) imaging framework, utilizing scenario-specific priors to conduct the path selection with an accuracy of more than 93. 3$\%$.
DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale
DeepSpeed Inference reduces latency by up to 7. 3X over the state-of-the-art for latency-oriented scenarios and increases throughput by over 1. 5x for throughput-oriented scenarios.
Rethinking Query-Key Pairwise Interactions in Vision Transformers
Vision Transformers have achieved state-of-the-art performance in many visual tasks.
BiFeat: Supercharge GNN Training via Graph Feature Quantization
We identify the main accuracy impact factors in graph feature quantization and theoretically prove that BiFeat training converges to a network where the loss is within $\epsilon$ of the optimal loss of uncompressed network.
SelfCoLearn: Self-supervised collaborative learning for accelerating dynamic MR imaging
Lately, deep learning has been extensively investigated for accelerating dynamic magnetic resonance (MR) imaging, with encouraging progresses achieved.
From WSI-level to Patch-level: Structure Prior Guided Binuclear Cell Fine-grained Detection
The coarse detection network is a multi-task detection framework based on circular bounding boxes for cells detection, and central key points for nucleus detection.
Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report
Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP).
DIGEST: Deeply supervIsed knowledGE tranSfer neTwork learning for brain tumor segmentation with incomplete multi-modal MRI scans
In this work, we propose a Deeply supervIsed knowledGE tranSfer neTwork (DIGEST), which achieves accurate brain tumor segmentation under different modality-missing scenarios.
Adaptive PromptNet For Auxiliary Glioma Diagnosis without Contrast-Enhanced MRI
Multi-contrast magnetic resonance imaging (MRI)-based automatic auxiliary glioma diagnosis plays an important role in the clinic.
Uncertainty-Aware Multi-Parametric Magnetic Resonance Image Information Fusion for 3D Object Segmentation
Multi-parametric magnetic resonance (MR) imaging is an indispensable tool in the clinic.
Semi-Supervised and Self-Supervised Collaborative Learning for Prostate 3D MR Image Segmentation
The proposed framework is very useful in clinical applications when training data with dense annotations are difficult to obtain.
Random-LTD: Random and Layerwise Token Dropping Brings Efficient Training for Large-scale Transformers
Large-scale transformer models have become the de-facto architectures for various machine learning applications, e. g., CV and NLP.
Iterative Data Refinement for Self-Supervised MR Image Reconstruction
Then, we design an effective self-supervised training data refinement method to reduce this data bias.
DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing
Compared to the rapidly evolving model architecture, how to efficiently use the training data (especially for the expensive foundation model pretraining) is both less explored and difficult to realize due to the lack of a convenient framework that focuses on data efficiency capabilities.
Style Projected Clustering for Domain Generalized Semantic Segmentation
In contrast to existing methods, we instead utilize the difference between images to build a better representation space, where the distinct style features are extracted and stored as the bases of representation.
Toward RAW Object Detection: A New Benchmark and a New Model
In many computer vision applications (e. g., robotics and autonomous driving), high dynamic range (HDR) data is necessary for object detection algorithms to handle a variety of lighting conditions, such as strong glare.
SuperScaler: Supporting Flexible DNN Parallelization via a Unified Abstraction
SuperScaler is a system that facilitates the design and generation of highly flexible parallelization plans.
Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases
Improving the deployment efficiency of transformer-based language models has been challenging given their high computation and memory cost.
MGA: Medical generalist agent through text-guided knowledge transformation
To this end, we propose a novel medical generalist agent, MGA, that can address three kinds of common clinical tasks via clinical reports knowledge transformation.
ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation
Post-training quantization (PTQ) has emerged as a promising technique for mitigating memory consumption and computational costs in large language models (LLMs).
Few-shot Class-incremental Learning for Cross-domain Disease Classification
The ability to incrementally learn new classes from limited samples is crucial to the development of artificial intelligence systems for real clinical application.
Model-based Federated Learning for Accurate MR Image Reconstruction from Undersampled k-space Data
However, high heterogeneity exists in the data from different centers, and existing federated learning methods tend to use average aggregation methods to combine the client's information, which limits the performance and generalization capability of the trained models.
Understand Data Preprocessing for Effective End-to-End Training of Deep Neural Networks
In this paper, we primarily focus on understanding the data preprocessing pipeline for DNN Training in the public cloud.
Self-Supervised Federated Learning for Fast MR Imaging
SSFedMRI explores the physics-based contrastive reconstruction networks in each client to realize cross-site collaborative training in the absence of fully sampled data.
Machine learning-based characterization of hydrochar from biomass: Implications for sustainable energy and material production
Hydrothermal carbonization (HTC) is a process that converts biomass into versatile hydrochar without the need for prior drying.
RestGPT: Connecting Large Language Models with Real-World RESTful APIs
To address the practical challenges of tackling complex instructions, we propose RestGPT, which exploits the power of LLMs and conducts a coarse-to-fine online planning mechanism to enhance the abilities of task decomposition and API selection.
Large Language Models Understand and Can be Enhanced by Emotional Stimuli
In addition to those deterministic tasks that can be automatically evaluated using existing metrics, we conducted a human study with 106 participants to assess the quality of generative tasks using both vanilla and emotional prompts.
FedAutoMRI: Federated Neural Architecture Search for MR Image Reconstruction
Centralized training methods have shown promising results in MR image reconstruction, but privacy concerns arise when gathering data from multiple institutions.
End-to-End Query Term Weighting
These inferred weights and terms can be used directly by a retrieval system to perform a query search.
Ranked #1 on
Passage Retrieval
on MS MARCO
Teach LLMs to Personalize -- An Approach inspired by Writing Education
Inspired by the practice of writing education, we develop a multistage and multitask framework to teach LLMs for personalized generation.
Self-distillation Regularized Connectionist Temporal Classification Loss for Text Recognition: A Simple Yet Effective Approach
It incorporates a framewise regularization term in CTC loss to emphasize individual supervision, and leverages the maximizing-a-posteriori of latent alignment to solve the inconsistency problem that arises in distillation between CTC-based models.
ChatHaruhi: Reviving Anime Character in Reality via Large Language Model
Role-playing chatbots built on large language models have drawn interest, but better techniques are needed to enable mimicking specific fictional characters.
Generalizable Learning Reconstruction for Accelerating MR Imaging via Federated Neural Architecture Search
Heterogeneous data captured by different scanning devices and imaging protocols can affect the generalization performance of the deep learning magnetic resonance (MR) reconstruction model.
PBFormer: Capturing Complex Scene Text Shape with Polynomial Band Transformer
We present PBFormer, an efficient yet powerful scene text detector that unifies the transformer with a novel text shape representation Polynomial Band (PB).
Enhancing Representation in Radiography-Reports Foundation Model: A Granular Alignment Algorithm Using Masked Contrastive Learning
Recently, multi-modal vision-language foundation models have gained significant attention in the medical field.
Learning to Rewrite Prompts for Personalized Text Generation
In this paper, we propose a novel method to automatically revise prompts for personalized text generation.
CrossZoom: Simultaneously Motion Deblurring and Event Super-Resolving
Even though the collaboration between traditional and neuromorphic event cameras brings prosperity to frame-event based vision applications, the performance is still confined by the resolution gap crossing two modalities in both spatial and temporal domains.
Automated Evaluation of Personalized Text Generation using Large Language Models
Personalized text generation presents a specialized mechanism for delivering content that is specific to a user's personal context.
InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews
This paper, instead, introduces a novel perspective to evaluate the personality fidelity of RPAs with psychological scales.
Tessel: Boosting Distributed Execution of Large DNN Models via Flexible Schedule Search
This paper presents Tessel, an automated system that searches for efficient schedules for distributed DNN training and inference for diverse operator placement strategies.
The Good, The Bad, and Why: Unveiling Emotions in Generative AI
Through extensive experiments involving language and multi-modal models on semantic understanding, logical reasoning, and generation tasks, we demonstrate that both textual and visual EmotionPrompt can boost the performance of AI models while EmotionAttack can hinder it.
Collaborative Learning for Annotation-Efficient Volumetric MR Image Segmentation
The other 100 (8, 800 image slices) are for left atrium segmentation.
Gemini: A Family of Highly Capable Multimodal Models
This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding.
Ranked #1 on
Multi-task Language Understanding
on MMLU
(using extra training data)
Cross-Modal Object Tracking via Modality-Aware Fusion Network and A Large-Scale Dataset
Visual tracking often faces challenges such as invalid targets and decreased performance in low-light conditions when relying solely on RGB image sequences.
DarkShot: Lighting Dark Images with Low-Compute and High-Quality
This paper proposes a lightweight network that outperforms existing state-of-the-art (SOTA) methods in low-light enhancement tasks while minimizing computation.
Multimodal self-supervised learning for lesion localization
Multimodal deep learning utilizing imaging and diagnostic reports has made impressive progress in the field of medical imaging diagnostics, demonstrating a particularly strong capability for auxiliary diagnosis in cases where sufficient annotation information is lacking.
AID-DTI: Accelerating High-fidelity Diffusion Tensor Imaging with Detail-Preserving Model-based Deep Learning
Deep learning has shown great potential in accelerating diffusion tensor imaging (DTI).
Modality Exchange Network for Retinogeniculate Visual Pathway Segmentation
Secondly, we propose a cross-fusion module that further enhances the fusion of information between the two modalities.
Simultaneous q-Space Sampling Optimization and Reconstruction for Fast and High-fidelity Diffusion Magnetic Resonance Imaging
Diffusion Magnetic Resonance Imaging (dMRI) plays a crucial role in the noninvasive investigation of tissue microstructural properties and structural connectivity in the \textit{in vivo} human brain.
MLIP: Medical Language-Image Pre-training with Masked Local Representation Learning
Existing contrastive language-image pre-training aims to learn a joint representation by matching abundant image-text pairs.
Enhancing Representation in Medical Vision-Language Foundation Models via Multi-Scale Information Extraction Techniques
The development of medical vision-language foundation models has attracted significant attention in the field of medicine and healthcare due to their promising prospect in various clinical applications.
LESEN: Label-Efficient deep learning for Multi-parametric MRI-based Visual Pathway Segmentation
Recent research has shown the potential of deep learning in multi-parametric MRI-based visual pathway (VP) segmentation.
Multi-modal vision-language model for generalizable annotation-free pathological lesions localization
Defining pathologies automatically from medical images aids the understanding of the emergence and progression of diseases, and such an ability is crucial in clinical diagnostics.
Bridging the Preference Gap between Retrievers and LLMs
Large Language Models (LLMs) have demonstrated superior results across a wide range of tasks, and Retrieval-augmented Generation (RAG) is an effective way to enhance the performance by locating relevant information and placing it into the context window of the LLM.
Enhancing the vision-language foundation model with key semantic knowledge-emphasized report refinement
Particularly, raw radiology reports are refined to highlight the key information according to a constructed clinical dictionary and two model-optimized knowledge-enhancement metrics.
Knowledge-driven deep learning for fast MR imaging: undersampled MR image reconstruction from supervised to un-supervised learning
The traits and trends of these techniques have also been given which have shifted from supervised learning to semi-supervised learning, and finally, to unsupervised learning methods.
Unlocking the `Why' of Buying: Introducing a New Dataset and Benchmark for Purchase Reason and Post-Purchase Experience
To this end, we introduce an LLM-based approach to generate a dataset that consists of textual explanations of why real users make certain purchase decisions.
Adversarial Testing for Visual Grounding via Image-Aware Property Reduction
To this end, we propose PEELING, a text perturbation approach via image-aware property reduction for adversarial testing of the VG model.
VEglue: Testing Visual Entailment Systems via Object-Aligned Joint Erasing
Visual entailment (VE) is a multimodal reasoning task consisting of image-sentence pairs whereby a promise is defined by an image, and a hypothesis is described by a sentence.
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
In this report, we present the latest model of the Gemini family, Gemini 1. 5 Pro, a highly compute-efficient multimodal mixture-of-experts model capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio.
Ranked #19 on
Code Generation
on HumanEval
Automating Vessel Segmentation in the Heart and Brain: A Trend to Develop Multi-Modality and Label-Efficient Deep Learning Techniques
Cardio-cerebrovascular diseases are the leading causes of mortality worldwide, whose accurate blood vessel segmentation is significant for both scientific research and clinical usage.
CSR-dMRI: Continuous Super-Resolution of Diffusion MRI with Anatomical Structure-assisted Implicit Neural Representation Learning
The first is the latent feature extractor, which primarily extracts latent space feature maps from LR dMRI and anatomical images while learning structural prior information from the anatomical images.
Improving Query Graph Generation for Complex Question Answering over Knowledge Base
Most of the existing Knowledge-based Question Answering (KBQA) methods first learn to map the given question to a query graph, and then convert the graph to an executable query to find the answer.
When does Further Pre-training MLM Help? An Empirical Study on Task-Oriented Dialog Pre-training
Further pre-training language models on in-domain data (domain-adaptive pre-training, DAPT) or task-relevant data (task-adaptive pre-training, TAPT) before fine-tuning has been shown to improve downstream tasks’ performances.
