Search Results for author:
Found 71 papers, 18 papers with code
Self-supervised Monocular Depth and Pose Estimation for Endoscopy with Generative Latent Priors
Accurate 3D mapping in endoscopy enables quantitative, holistic lesion characterization within the gastrointestinal (GI) tract, requiring reliable depth and pose estimation.
FM-TS: Flow Matching for Time Series Generation
FM-TS is more efficient in terms of training and inference.
Primal-Dual Spectral Representation for Off-policy Evaluation
We highlight that our algorithm, SpectralDICE, is the first to leverage the linear representation of primal-dual variables that is both computation and sample efficient, the performance of which is supported by a rigorous theoretical sample complexity guarantee and a thorough empirical evaluation on various benchmarks.
Risk-sensitive Affine Control Synthesis for Stationary LTI Systems
To address deviations from expected performance in stochastic systems, we propose a risk-sensitive control synthesis method to minimize certain risk measures over the limiting stationary distribution.
HE-Drive: Human-Like End-to-End Driving with Vision Language Models
In this paper, we propose HE-Drive: the first human-like-centric end-to-end autonomous driving system to generate trajectories that are both temporally consistent and comfortable.
Continual Learning for Remote Physiological Measurement: Minimize Forgetting and Simplify Inference
Meanwhile, most existing class incremental learning approaches are unsuitable for rPPG measurement.
In-depth analysis of recall initiators of medical devices with a Machine Learning-Natural language Processing workflow
Recall initiator identification and assessment are the preliminary steps to prevent medical device recall.
Efficient Orchestrated AI Workflows Execution on Scale-out Spatial Architecture
Given the increasing complexity of AI applications, traditional spatial architectures frequently fall short.
IFNet: Deep Imaging and Focusing for Handheld SAR with Millimeter-wave Signals
Recent advancements have showcased the potential of handheld millimeter-wave (mmWave) imaging, which applies synthetic aperture radar (SAR) principles in portable settings.
Shifting Spotlight for Co-supervision: A Simple yet Efficient Single-branch Network to See Through Camouflage
Efficient and accurate camouflaged object detection (COD) poses a challenge in the field of computer vision.
Efficient Duple Perturbation Robustness in Low-rank MDPs
The pursuit of robustness has recently been a popular topic in reinforcement learning (RL) research, yet the existing methods generally suffer from efficiency issues that obstruct their real-world implementation.
Leveraging Intelligent Recommender system as a first step resilience measure -- A data-driven supply chain disruption response framework
Interests in the value of digital technologies for its potential uses to increase supply chain resilience (SCRes) are increasing in light to the industry 4. 0 and the global pandemic.
Emulating Complex Synapses Using Interlinked Proton Conductors
The memory consolidation from coupled storage components is revealed by both numerical simulations and experimental observations.
Passive Non-Line-of-Sight Imaging with Light Transport Modulation
In this work, we propose NLOS-LTM, a novel passive NLOS imaging method that effectively handles multiple light transport conditions with a single network.
Semantic Connectivity-Driven Pseudo-labeling for Cross-domain Segmentation
This approach formulates pseudo-labels at the connectivity level and thus can facilitate learning structured and low-noise semantics.
DREAM-PCD: Deep Reconstruction and Enhancement of mmWave Radar Pointcloud
However, existing methods failed to simultaneously address the three main challenges in mmWave radar pointcloud reconstruction: specular information lost, low angular resolution, and strong interference and noise.
Beyond attention: deriving biologically interpretable insights from weakly-supervised multiple-instance learning models
Recent advances in attention-based multiple instance learning (MIL) have improved our insights into the tissue regions that models rely on to make predictions in digital pathology.
Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity
This paper introduces a new formulation for risk-sensitive MDPs, which assesses risk in a slightly different manner compared to the classical Markov risk measure (Ruszczy\'nski 2010), and establishes its equivalence with a class of soft robust MDP (RMDP) problems, including the standard RMDP as a special case.
Perspectives in closed-loop supply chains network design considering risk and uncertainty factors
Risk and uncertainty in each stage of CLSC have greatly increased the complexity and reduced process efficiency of the closed-loop networks, impeding the sustainable and resilient development of industries and the circular economy.
Catch-Up Distillation: You Only Need to Train Once for Accelerating Sampling
On CIFAR-10, we obtain a FID of 2. 80 by sampling in 15 steps under one-session training and the new state-of-the-art FID of 3. 37 by sampling in one step with additional training.
A Dynamic-Neighbor Particle Swarm Optimizer for Accurate Latent Factor Analysis
High-Dimensional and Incomplete matrices, which usually contain a large amount of valuable latent information, can be well represented by a Latent Factor Analysis model.
DLBD: A Self-Supervised Direct-Learned Binary Descriptor
Since their binarization processes are not a component of the network, the learning-based binary descriptor cannot fully utilize the advances of deep learning.
RFPose-OT: RF-Based 3D Human Pose Estimation via Optimal Transport Theory
Different from existing methods that predict human poses from RF signals on the signal level directly, we consider the structure difference between the RF signals and the human poses, propose to transform the RF signals to the pose domain on the feature level based on Optimal Transport (OT) theory, and generate human poses from the transformed features.
Modeling Hierarchical Structural Distance for Unsupervised Domain Adaptation
Compared with the ground distance of the conventional domain-level OT, the image-level OT captures structural associations among local regions of images that are beneficial to classification.
Two-Dimensional Weisfeiler-Lehman Graph Neural Networks for Link Prediction
As pointed out by previous works, this two-step procedure results in low discriminating power, as 1-WL-GNNs by nature learn node-level representations instead of link-level.
NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results
The challenge is composed of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i. e. solutions can not exceed a given number of operations).
Attention-based CNN-LSTM and XGBoost hybrid model for stock prediction
Due to the complex volatility of the stock market, the research and prediction on the change of the stock price, can avoid the risk for the investors.
Enabling Efficient Deep Convolutional Neural Network-based Sensor Fusion for Autonomous Driving
We also propose a Layer-sharing technique in the deep layer that can achieve better accuracy with less computational overhead.
SapientML: Synthesizing Machine Learning Pipelines by Learning from Human-Written Solutions
In this work we propose an AutoML technique SapientML, that can learn from a corpus of existing datasets and their human-written pipelines, and efficiently generate a high-quality pipeline for a predictive task on a new dataset.
RFMask: A Simple Baseline for Human Silhouette Segmentation with Radio Signals
To overcome such limitations, in this paper, we propose to utilize the radio signals, which can traverse obstacles and are unaffected by the lighting conditions to achieve silhouette segmentation.
Radio-Assisted Human Detection
In this paper, we propose a radio-assisted human detection framework by incorporating radio information into the state-of-the-art detection methods, including anchor-based onestage detectors and two-stage detectors.
Learning Token-based Representation for Image Retrieval
Next, a refinement block is introduced to enhance the visual tokens with self-attention and cross-attention.
Ranked #2 on
Image Retrieval
on RParis (Medium)
RFGAN: RF-Based Human Synthesis
To the best of our knowledge, this is the first work to generate optical images based on RF signals.
Unsupervised Domain Adaptation for RF-based Gesture Recognition
Then we propose a confidence constraint loss to enhance the effectiveness of pseudo-labeling, and design two corresponding data augmentation methods based on the characteristic of the RF signals to strengthen the performance of the consistency regularization, which can make the framework more effective and robust.
Calculus of Consent via MARL: Legitimating the Collaborative Governance Supplying Public Goods
Experimental results in an exemplary environment show that our MARL approach is able to demonstrate the effectiveness and necessity of restrictions on individual liberty for collaborative supply of public goods.
Towards Domain-Independent and Real-Time Gesture Recognition Using mmWave Signal
To enhance the robustness of the system and reduce data collecting efforts, we design a data augmentation framework for mmWave signals based on correlations between signal patterns and gesture variations.
Pipeline Parallelism for Inference on Heterogeneous Edge Computing
We propose EdgePipe, a distributed framework for edge systems that uses pipeline parallelism to both speed up inference and enable running larger (and more accurate) models that otherwise cannot fit on single edge devices.
NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks
Aiming to make GNN improvements practical, this paper proposes an approach called NeuroBack, which builds on two insights: (1) predicting phases (i. e., values) of variables appearing in the majority (or even all) of the satisfying assignments are essential for CDCL SAT solving, and (2) it is sufficient to query the neural model only once for the predictions before the SAT solving starts.
Containerized Distributed Value-Based Multi-Agent Reinforcement Learning
Multi-agent reinforcement learning tasks put a high demand on the volume of training samples.
Intervention Adversarial Auto-Encoder
In this paper we propose a new method to stabilize the training process of the latent variables of adversarial auto-encoders, which we name Intervention Adversarial auto-encoder (IVAAE).
Heredity-aware Child Face Image Generation with Latent Space Disentanglement
The main idea is to disentangle the latent space of a pre-trained generation model and precisely control the face attributes of child images with clear semantics.
Personalized Outfit Recommendation With Learnable Anchors
To accommodate the variety of users' preferences, we characterize each user with a set of anchors, i. e. a group of learnable latent vectors in the outfit space that are the representatives of the outfits the user likes.
What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data
Supervised machine learning has several drawbacks that make it difficult to use in many situations.
Graph-MLP: Node Classification without Message Passing in Graph
Graph Neural Network (GNN) has been demonstrated its effectiveness in dealing with non-Euclidean structural data.
Recent Advances on Non-Line-of-Sight Imaging: Conventional Physical Models, Deep Learning, and New Scenes
As an emerging technology that has attracted huge attention, non-line-of-sight (NLOS) imaging can reconstruct hidden objects by analyzing the diffuse reflection on a relay surface, with broad application prospects in the fields of autonomous driving, medical imaging, and defense.
Tackling Variabilities in Autonomous Driving
In this work, we aim to extensively explore the above system design challenges and these challenges motivate us to propose a comprehensive framework that synergistically handles the heterogeneous hardware accelerator design principles, system design criteria, and task scheduling mechanism.
Graph-based Visual-Semantic Entanglement Network for Zero-shot Image Recognition
Zero-shot learning uses semantic attributes to connect the search space of unseen objects.
Multiple Attentional Pyramid Networks for Chinese Herbal Recognition
Finally, a new framework for Chinese herbal recognition is proposed as a new application of APN.
Data Augmentation Imbalance For Imbalanced Attribute Classification
Pedestrian attribute recognition is an important multi-label classification problem.
Neural Architecture Search For Fault Diagnosis
In this paper, we proposed a NAS method for fault diagnosis using reinforcement learning.
Deep Reinforcement Learning with Modulated Hebbian plus Q Network Architecture
This paper presents a new neural architecture that combines a modulated Hebbian network (MOHN) with DQN, which we call modulated Hebbian plus Q network architecture (MOHQA).
Skill Transfer in Deep Reinforcement Learning under Morphological Heterogeneity
We demonstrate its performance compared to a state-of-the-art approach and several ablation cases, visualize and interpret the hidden factors, and identify avenues for future improvements.
A Multi-Scale Mapping Approach Based on a Deep Learning CNN Model for Reconstructing High-Resolution Urban DEMs
Few attempts have been made for urban topography which is typically an integration of complex man-made and natural features.
Stochastic Region Pooling: Make Attention More Expressive
Global Average Pooling (GAP) is used by default on the channel-wise attention mechanism to extract channel descriptors.
Inner-Imaging Networks: Put Lenses into Convolutional Structure
To deal with these problems, a novel Inner-Imaging architecture is proposed in this paper, which allows relationships between channels to meet the above requirement.
Chinese Herbal Recognition based on Competitive Attentional Fusion of Multi-hierarchies Pyramid Features
According to the characteristics of herbal images, we proposed the competitive attentional fusion pyramid networks to model the features of herbal image, which mdoels the relationship of feature maps from different levels, and re-weights multi-level channels with channel-wise attention mechanism.
Convolutional herbal prescription building method from multi-scale facial features
In order to mine features from different granularities of faces, we design a multi-scale convolutional neural network based on three-grained face, which mines the patient's face information from the organs, local regions, and the entire face.
Solution for Large-Scale Hierarchical Object Detection Datasets with Incomplete Annotation and Data Imbalance
This report demonstrates our solution for the Open Images 2018 Challenge.
Feature Learning for Fault Detection in High-Dimensional Condition-Monitoring Signals
The performance is first evaluated on a synthetic dataset that encompasses typical characteristics of condition monitoring data.
FashionNet: Personalized Outfit Recommendation with Deep Neural Network
Our system, dubbed FashionNet, consists of two components, a feature network for feature extraction and a matching network for compatibility computation.
Metabolize Neural Network
It is self-evident that the significance of metabolize neuronal network(MetaNet) in model construction.
Competitive Inner-Imaging Squeeze and Excitation for Residual Network
In this work, we propose a competitive squeeze-excitation (SE) mechanism for the residual network.
A Fully Convolutional Two-Stream Fusion Network for Interactive Image Segmentation
The proposed network includes two sub-networks: a two-stream late fusion network (TSLFN) that predicts the foreground at a reduced resolution, and a multi-scale refining network (MSRN) that refines the foreground at full resolution.
Tongue image constitution recognition based on Complexity Perception method
To evaluate the performance of our proposed method, we conduct experiments on three sizes of tongue datasets, in which deep convolutional neural network method and traditional digital image analysis method are respectively applied to extract features for tongue images.
Facial Expression Recognition Based on Complexity Perception Classification Algorithm
Facial expression recognition (FER) has always been a challenging issue in computer vision.
Automatic construction of Chinese herbal prescription from tongue image via CNNs and auxiliary latent therapy topics
In order to adapt to the tongue image in a variety of photographic environments and construct herbal prescriptions, a neural network framework for prescription construction is designed.
Multi-stage Suture Detection for Robot Assisted Anastomosis based on Deep Learning
In robotic surgery, task automation and learning from demonstration combined with human supervision is an emerging trend for many new surgical robot platforms.
Endoscopic Depth Measurement and Super-Spectral-Resolution Imaging
Intra-operative measurements of tissue shape and multi/ hyperspectral information have the potential to provide surgical guidance and decision making support.
Open-set Person Re-identification
Person re-identification is becoming a hot research for developing both machine learning algorithms and video surveillance applications.
Person Re-identification by Local Maximal Occurrence Representation and Metric Learning
In this paper, we propose an effective feature representation called Local Maximal Occurrence (LOMO), and a subspace and metric learning method called Cross-view Quadratic Discriminant Analysis (XQDA).
Ranked #91 on
Person Re-Identification
on DukeMTMC-reID
Fast Matching by 2 Lines of Code for Large Scale Face Recognition Systems
However, the use of this method is very generic and not limited in face recognition, which can be easily generalized to other biometrics as a post-processing module.
