Search Results for author:
Found 73 papers, 21 papers with code
Couler: Unified Machine Learning Workflow Optimization in Cloud
This variety poses a challenge for end-users in terms of mastering different engine APIs.
PPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of Multi-Agent Reinforcement Learning
Agents share Q-value network periodically during the training process.
Nearest Neighbour Score Estimators for Diffusion Generative Models
Score function estimation is the cornerstone of both training and sampling from diffusion generative models.
Multi-Level Aggregation and Recursive Alignment Architecture for Efficient Parallel Inference Segmentation Network
Real-time semantic segmentation is a crucial research for real-world applications.
Deep Efficient Private Neighbor Generation for Subgraph Federated Learning
Behemoth graphs are often fragmented and separately stored by multiple data owners as distributed subgraphs in many realistic applications.
ASPEN: High-Throughput LoRA Fine-Tuning of Large Language Models with a Single GPU
Transformer-based large language models (LLMs) have demonstrated outstanding performance across diverse domains, particularly when fine-turned for specific domains.
AGD: an Auto-switchable Optimizer using Stepwise Gradient Difference for Preconditioning Matrix
Additionally, we introduce an auto-switching function that enables the preconditioning matrix to switch dynamically between Stochastic Gradient Descent (SGD) and the adaptive optimizer.
Developing a Novel Image Marker to Predict the Responses of Neoadjuvant Chemotherapy (NACT) for Ovarian Cancer Patients
To address this clinical challenge, the purpose of this study is to develop a novel image marker to achieve high accuracy response prediction of the NACT at an early stage.
ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection
The results demonstrate that ImGeoNet outperforms the current state-of-the-art multi-view image-based method, ImVoxelNet, on all three datasets in terms of detection accuracy.
Ranked #24 on
3D Object Detection
on ScanNetV2
ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation
Large-scale Pre-Training Vision-Language Model such as CLIP has demonstrated outstanding performance in zero-shot classification, e. g. achieving 76. 3% top-1 accuracy on ImageNet without seeing any example, which leads to potential benefits to many tasks that have no labeled data.
Spatio-Temporal Classification of Lung Ventilation Patterns using 3D EIT Images: A General Approach for Individualized Lung Function Evaluation
A simple convolutional neural network is used for classification.
Sharpness-Aware Minimization Revisited: Weighted Sharpness as a Regularization Term
Deep Neural Networks (DNNs) generalization is known to be closely related to the flatness of minima, leading to the development of Sharpness-Aware Minimization (SAM) for seeking flatter minima and better generalization.
Multi-task Paired Masking with Alignment Modeling for Medical Vision-Language Pre-training
To address this limitation, we propose a unified Med-VLP framework based on Multi-task Paired Masking with Alignment (MPMA) to integrate the cross-modal alignment task into the joint image-text reconstruction framework to achieve more comprehensive cross-modal interaction, while a Global and Local Alignment (GLA) module is designed to assist self-supervised paradigm in obtaining semantic representations with rich domain knowledge.
Predict NAS Multi-Task by Stacking Ensemble Models using GP-NAS
In this track, Super Network builds a search space based on ViT-Base.
Construct sparse portfolio with mutual fund's favourite stocks in China A share market
Therefore, in order to get excess return from mutual fund industry, we use quantitative way to build the sparse portfolio that take advantage of favorite stocks by mutual fund in China A market.
DLRover: An Elastic Deep Training Extension with Auto Job Resource Recommendation
The resource configuration of a job deeply affect this job's performance (e. g., training throughput, resource utilization, and completion rate).
Adjust factor with volatility model using MAXFLAT low-pass filter and construct portfolio in China A share market
Our result shows adjust factors by MAXFLAT volatility model have better performance in both large cap and small cap universe than original factors or other risk adjust factors in China A share.
Evaluating the Effectiveness of 2D and 3D Features for Predicting Tumor Response to Chemotherapy
2D and 3D tumor features are widely used in a variety of medical image analysis tasks.
ZScribbleSeg: Zen and the Art of Scribble Supervised Medical Image Segmentation
Curating a large scale fully-annotated dataset can be both labour-intensive and expertise-demanding, especially for medical images.
CameraPose: Weakly-Supervised Monocular 3D Human Pose Estimation by Leveraging In-the-wild 2D Annotations
By adding a camera parameter branch, any in-the-wild 2D annotations can be fed into our pipeline to boost the training diversity and the 3D poses can be implicitly learned by reprojecting back to 2D.
Ranked #68 on
3D Human Pose Estimation
on Human3.6M
BUMP: A Benchmark of Unfaithful Minimal Pairs for Meta-Evaluation of Faithfulness Metrics
The proliferation of automatic faithfulness metrics for summarization has produced a need for benchmarks to evaluate them.
Multi-head Uncertainty Inference for Adversarial Attack Detection
We adopt a multi-head architecture with multiple prediction heads (i. e., classifiers) to obtain predictions from different depths in the DNNs and introduce shallow information for the UI.
MyoPS-Net: Myocardial Pathology Segmentation with Flexible Combination of Multi-Sequence CMR Images
We therefore conducted extensive experiments to investigate the performance of the proposed method in dealing with such complex combinations of different CMR sequences.
CrisisLTLSum: A Benchmark for Local Crisis Event Timeline Extraction and Summarization
This paper presents CrisisLTLSum, the largest dataset of local crisis event timelines available to date.
Transformers Improve Breast Cancer Diagnosis from Unregistered Multi-View Mammograms
For this purpose, we employ local Transformer blocks to separately learn patch relationships within four mammograms acquired from two-view (CC/MLO) of two-side (right/left) breasts.
Deep Compatible Learning for Partially-Supervised Medical Image Segmentation
To address the challenge, we propose a deep compatible learning (DCL) framework, which trains a single multi-label segmentation network using images with only partial structures annotated.
An Exploration of Post-Editing Effectiveness in Text Summarization
Automatic summarization methods are efficient but can suffer from low quality.
ShapePU: A New PU Learning Framework Regularized by Global Consistency for Scribble Supervised Cardiac Segmentation
To tackle this problem, we propose a new scribble-guided method for cardiac segmentation, based on the Positive-Unlabeled (PU) learning framework and global consistency regularization, and termed as ShapePU.
Parallel Network with Channel Attention and Post-Processing for Carotid Arteries Vulnerable Plaque Segmentation in Ultrasound Images
Test results show that the proposed method with dice loss function yields a Dice value of 0. 820, an IoU of 0. 701, Acc of 0. 969, and modified Hausdorff distance (MHD) of 1. 43 for 30 vulnerable cases of plaques, it outperforms some of the conventional CNN-based methods on these metrics.
InsCon:Instance Consistency Feature Representation via Self-Supervised Learning
On the other hand, InsCon introduces the pull and push of cell-instance, which utilizes cell consistency to enhance fine-grained feature representation for precise boundary localization.
CEKD:Cross Ensemble Knowledge Distillation for Augmented Fine-grained Data
We innovatively propose a cross distillation module to provide additional supervision to alleviate the noise problem, and propose a collaborative ensemble module to overcome the target conflict problem.
CycleMix: A Holistic Strategy for Medical Image Segmentation from Scribble Supervision
To address the difficulties, we propose a new framework for scribble learning-based medical image segmentation, which is composed of mix augmentation and cycle consistency and thus is referred to as CycleMix.
Ranked #3 on
Semantic Segmentation
on ACDC Scribbles
Parallel Spatio-Temporal Attention-Based TCN for Multivariate Time Series Prediction
As industrial systems become more complex and monitoring sensors for everything from surveillance to our health become more ubiquitous, multivariate time series prediction is taking an important place in the smooth-running of our society.
Virtual Adversarial Training for Semi-supervised Breast Mass Classification
This study aims to develop a novel computer-aided diagnosis (CAD) scheme for mammographic breast mass classification using semi-supervised learning.
TriCoLo: Trimodal Contrastive Loss for Text to Shape Retrieval
Text-to-shape retrieval is an increasingly relevant problem with the growth of 3D shape data.
Maximize the Exploration of Congeneric Semantics for Weakly Supervised Semantic Segmentation
The graph network that is established with patches as the nodes can maximize the mutual learning of similar objects.
Subgraph Federated Learning with Missing Neighbor Generation
Graphs have been widely used in data mining and machine learning due to their unique representation of real-world objects and their interactions.
A Review of Human Evaluation for Style Transfer
However, in style transfer papers, we find that protocols for human evaluations are often underspecified and not standardized, which hampers the reproducibility of research in this field and progress toward better human and automatic evaluation methods.
Ol\'a, Bonjour, Salve! XFORMAL: A Benchmark for Multilingual Formality Style Transfer
We take the first step towards multilingual style transfer by creating and releasing XFORMAL, a benchmark of multiple formal reformulations of informal text in Brazilian Portuguese, French, and Italian.
Recent advances and clinical applications of deep learning in medical image analysis
Deep learning has received extensive research interest in developing new medical image processing algorithms, and deep learning based models have been remarkably successful in a variety of medical imaging tasks to support disease detection and diagnosis.
Structure Guided Lane Detection
Next, multi-level structural constraints are used to improve the perception of lanes.
Ranked #29 on
Lane Detection
on CULane
XFORMAL: A Benchmark for Multilingual Formality Style Transfer
We take the first step towards multilingual style transfer by creating and releasing XFORMAL, a benchmark of multiple formal reformulations of informal text in Brazilian Portuguese, French, and Italian.
Compacting Deep Neural Networks for Internet of Things: Methods and Applications
Deep Neural Networks (DNNs) have shown great success in completing complex tasks.
Destruction of refractory carbon grains drives the final stage of proto-planetary disk chemistry
To elevate the volatile C/O ratio, additional carbon has to be released into the gas to enable an equilibrium chemistry under oxygen-poor conditions.
Earth and Planetary Astrophysics Solar and Stellar Astrophysics
Efficient erbium-doped thin-film lithium niobate waveguide amplifiers
Lithium niobate on insulator (LNOI) is an emerging photonic platform with great promises for future optical communications, nonlinear optics and microwave photonics.
Optics Applied Physics
Probing fast oscillating scalar dark matter with atoms and molecules
We discuss the WReSL experiment, report on progress towards improved measurements of rapid fundamental constant variations, and discuss the planned extension of the work to molecules, in which rapid variations of the nuclear mass can be sensitively searched for.
Atomic Physics High Energy Physics - Phenomenology
Deep Reinforcement Learning for Stochastic Computation Offloading in Digital Twin Networks
Then, we formulate the stochastic computation offloading and resource allocation problem to minimize the long-term energy efficiency.
Recognition and standardization of cardiac MRI orientation via multi-tasking learning and deep neural networks
We embed the orientation recognition network in a Cardiac MRI Orientation Adjust Tool, i. e., CMRadjustNet.
Deep Reinforcement Learning and Permissioned Blockchain for Content Caching in Vehicular Edge Computing and Networks
In this paper, we integrate DRL and permissioned blockchain into vehicular networks for intelligent and secure content caching.
Anatomy Prior Based U-net for Pathology Segmentation with Attention
Pathological area segmentation in cardiac magnetic resonance (MR) images plays a vital role in the clinical diagnosis of cardiovascular diseases.
Edge Intelligence for Energy-efficient Computation Offloading and Resource Allocation in 5G Beyond
In this paper, we utilize DRL to design an optimal computation offloading and resource allocation strategy for minimizing system energy consumption.
Low-latency Federated Learning and Blockchain for Edge Association in Digital Twin empowered 6G Networks
In this paper, we introduce the Digital Twin Wireless Networks (DTWN) by incorporating digital twins into wireless networks, to migrate real-time data processing and computation to the edge plane.
Secure Network Release with Link Privacy
Many data mining and analytical tasks rely on the abstraction of networks (graphs) to summarize relational structures among individuals (nodes).
MU-GAN: Facial Attribute Editing based on Multi-attention Mechanism
Facial attribute editing has mainly two objectives: 1) translating image from a source domain to a target one, and 2) only changing the facial regions related to a target attribute and preserving the attribute-excluding details.
Secure Deep Graph Generation with Link Differential Privacy
Many data mining and analytical tasks rely on the abstraction of networks (graphs) to summarize relational structures among individuals (nodes).
Multi-Vehicle Routing Problems with Soft Time Windows: A Multi-Agent Reinforcement Learning Approach
Multi-vehicle routing problem with soft time windows (MVRPSTW) is an indispensable constituent in urban logistics distribution systems.
Computational Efficiency
Multi-agent Reinforcement Learning
+2
Detection Method Based on Automatic Visual Shape Clustering for Pin-Missing Defect in Transmission Lines
In this paper, an automatic detection model called Automatic Visual Shape Clustering Network (AVSCNet) for pin-missing defect is constructed.
Competing Ratio Loss for Discriminative Multi-class Image Classification
However, during the training of the deep convolutional neural network, the value of NLLR is not always positive or negative, which severely affects the convergence of NLLR.
Unsupervised Detection of Sub-events in Large Scale Disasters
Given the large amounts of posts, a major challenge is identifying the information that is useful and actionable.
Nanoconfined, dynamic electrolyte gating and memory effects in multilayered graphene-based membranes
Multilayered graphene-based nanoporous membranes with electrolyte incorporated between individual sheets is a unique nano-heterostructure system in which nanoconfined electrons in graphene and ions confined in between sheets are intimately coupled throughout the entire membrane.
Mesoscale and Nanoscale Physics Materials Science Soft Condensed Matter Applied Physics Chemical Physics
Controllable Length Control Neural Encoder-Decoder via Reinforcement Learning
Here, we denote a concept of Controllable Length Control (CLC) for the trade-off between length control capacity and semantic accuracy of the language generation model.
Competing Ratio Loss for Discriminative Multi-class Image Classification
A lot of studies of image classification based on deep convolutional neural network focus on the network structure to improve the image classification performance.
Hybrid Function Sparse Representation towards Image Super Resolution
Based on the idea of making the magnification of function curve without losing its fidelity, we proposed a function based dictionary on sparse representation for super resolution, called hybrid function sparse representation (HFSR).
Retrospective Encoders for Video Summarization
The key idea is to complement the discriminative losses with another loss which measures if the predicted summary preserves the same information as in the original video.
Machine Learning at the Edge: A Data-Driven Architecture with Applications to 5G Cellular Networks
Then, we will describe how the controllers can be used to run ML algorithms to predict the number of users in each base station, and a use case in which these predictions are exploited by a higher-layer application to route vehicular traffic according to network Key Performance Indicators (KPIs).
Fine-Grained Age Estimation in the wild with Attention LSTM Networks
Then, we fine-tune the ResNets or the RoR on the target age datasets to extract the global features of face images.
Ranked #4 on
Age And Gender Classification
on Adience Age
(using extra training data)
The Sea Exploration Problem: Data-driven Orienteering on a Continuous Surface
This paper describes a problem arising in sea exploration, where the aim is to schedule the expedition of a ship for collecting information about the resources on the seafloor.
Age Group and Gender Estimation in the Wild with Deep RoR Architecture
In this paper, we propose a new CNN based method for age group and gender estimation leveraging Residual Networks of Residual Networks (RoR), which exhibits better optimization ability for age group and gender classification than other CNN architectures. Moreover, two modest mechanisms based on observation of the characteristics of age group are presented to further improve the performance of age estimation. In order to further improve the performance and alleviate over-fitting problem, RoR model is pre-trained on ImageNet firstly, and then it is fune-tuned on the IMDB-WIKI-101 data set for further learning the features of face images, finally, it is used to fine-tune on Adience data set.
Ranked #6 on
Age And Gender Classification
on Adience Age
(using extra training data)
Pyramidal RoR for Image Classification
The Residual Networks of Residual Networks (RoR) exhibits excellent performance in the image classification task, but sharply increasing the number of feature map channels makes the characteristic information transmission incoherent, which losses a certain of information related to classification prediction, limiting the classification performance.
Residual Networks of Residual Networks: Multilevel Residual Networks
This paper proposes a novel residual-network architecture, Residual networks of Residual networks (RoR), to dig the optimization ability of residual networks.
Ranked #16 on
Image Classification
on SVHN
Video Summarization with Long Short-term Memory
We propose a novel supervised learning technique for summarizing videos by automatically selecting keyframes or key subshots.
Summary Transfer: Exemplar-based Subset Selection for Video Summarization
Video summarization has unprecedented importance to help us digest, browse, and search today's ever-growing video collections.
Gaming the Game: Honeypot Venues Against Cheaters in Location-based Social Networks
LBSNs offer a number of conveniences to its participants, such as - but not limited to - a list of places in the vicinity of a user, recommendations for an area never explored before provided by other peers, tracking of friends, monetary rewards in the form of special deals from the venues visited as well as a cheap way of advertisement for the latter.
Social and Information Networks Cryptography and Security
