Search Results for author:
Found 105 papers, 34 papers with code
Recovering from Privacy-Preserving Masking with Large Language Models
To effectively perform adaptation, textual data of users is typically stored on servers or their local devices, where downstream natural language processing (NLP) models can be directly trained using such in-domain data.
Sparse Federated Training of Object Detection in the Internet of Vehicles
However, the current object detection methods are mostly based on centralized deep training, that is, the sensitive data obtained by edge devices need to be uploaded to the server, which raises privacy concerns.
Diffusion-based 3D Object Detection with Random Boxes
3D object detection is an essential task for achieving autonomous driving.
Contextual Biasing of Named-Entities with Large Language Models
We propose to leverage prompts for a LLM without fine tuning during rescoring which incorporate a biasing list and few-shot examples to serve as additional information when calculating the score for the hypothesis.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
OnUVS: Online Feature Decoupling Framework for High-Fidelity Ultrasound Video Synthesis
Second, to better preserve the integrity and textural information of US images, we implemented a dual-decoder that decouples the content and textural features in the generator.
RLSAC: Reinforcement Learning enhanced Sample Consensus for End-to-End Robust Estimation
Therefore, RLSAC can avoid differentiating to learn the features and the feedback of downstream tasks for end-to-end robust estimation.
End-to-end 2D-3D Registration between Image and LiDAR Point Cloud for Vehicle Localization
A popular approach to robot localization is based on image-to-point cloud registration, which combines illumination-invariant LiDAR-based mapping with economical image-based localization.
G$^2$uardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clustering
As a collaborative paradigm, Federated Learning (FL) empowers clients to engage in collective model training without exchanging their respective local data.
SAM3D: Zero-Shot 3D Object Detection via Segment Anything Model
In the spirit of unleashing the capability of foundation models on vision tasks, the Segment Anything Model (SAM), a vision foundation model for image segmentation, has been proposed recently and presents strong zero-shot ability on many downstream 2D tasks.
E-NER: Evidential Deep Learning for Trustworthy Named Entity Recognition
Most named entity recognition (NER) systems focus on improving model performance, ignoring the need to quantify model uncertainty, which is critical to the reliability of NER systems in open environments.
Multi-Modal 3D Object Detection by Box Matching
Extensive experiments on the nuScenes dataset demonstrate that our method is much more stable in dealing with challenging cases such as asynchronous sensors, misaligned sensor placement, and degenerated camera images than existing fusion methods.
Ranked #47 on
3D Object Detection
on nuScenes
RARE: Robust Masked Graph Autoencoder
To address this issue, we propose a novel SGP method termed Robust mAsked gRaph autoEncoder (RARE) to improve the certainty in inferring masked data and the reliability of the self-supervision mechanism by further masking and reconstructing node samples in the high-order latent feature space.
Regularized Shallow Image Prior for Electrical Impedance Tomography
The results suggest that combining the shallow image prior and the hand-crafted regularization can achieve similar performance to the Deep Image Prior (DIP) but with less architectural dependency and complexity of the neural network.
RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration
Specifically, a projection-aware hierarchical transformer is proposed to capture long-range dependencies and filter outliers by extracting point features globally.
Mode-locking Theory for Long-Range Interaction in Artificial Neural Networks
We verify this theory through simulation experiments and demonstrate the mode-locking pattern in real-world scene models.
DDS3D: Dense Pseudo-Labels with Dynamic Threshold for Semi-Supervised 3D Object Detection
In this paper, we present a simple yet effective semi-supervised 3D object detector named DDS3D.
Distilled Reverse Attention Network for Open-world Compositional Zero-Shot Learning
Open-World Compositional Zero-Shot Learning (OW-CZSL) aims to recognize new compositions of seen attributes and objects.
Efficient and Low Overhead Website Fingerprinting Attacks and Defenses based on TCP/IP Traffic
To achieve a configurable trade-off between the defense and the network overhead, we further improve the list-based defense by a traffic splitting mechanism, which can combat the mentioned attacks as well as save a considerable amount of network overhead.
Auto-weighted Multi-view Clustering for Large-scale Data
Multi-view clustering has gained broad attention owing to its capacity to exploit complementary information across multiple data views.
StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-based 3D Object Detection
In this paper, we propose a cross-modal distillation method named StereoDistill to narrow the gap between the stereo and LiDAR-based approaches via distilling the stereo detectors from the superior LiDAR model at the response level, which is usually overlooked in 3D object detection distillation.
Adaptive Multi-Corpora Language Model Training for Speech Recognition
Thus, the data sampling strategy is important to the adaptation performance.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Hilbert Distillation for Cross-Dimensionality Networks
Since the distilled 2D networks are supervised by the curves converted from dimensionally heterogeneous 3D features, the 2D networks are given an informative view in terms of learning structural information embedded in well-trained high-dimensional representations.
Simple Primitives with Feasibility- and Contextuality-Dependence for Open-World Compositional Zero-shot Learning
We design Semantic Attention (SA) and generative Knowledge Disentanglement (KD) to learn the dependence of feasibility and contextuality, respectively.
Mitigating Unintended Memorization in Language Models via Alternating Teaching
Recent research has shown that language models have a tendency to memorize rare or unique sequences in the training corpora which can thus leak sensitive attributes of user data.
Group Personalized Federated Learning
Federated learning (FL) can help promote data privacy by training a shared model in a de-centralized manner on the physical devices of clients.
Modeling Dependent Structure for Utterances in ASR Evaluation
In this paper, we present graphical lasso based methods to explicitly model such dependency and estimate uncorrelated blocks of utterances in a rigorous way, after which blockwise bootstrap is applied on top of the inferred blocks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
PromptAttack: Prompt-based Attack for Language Models via Gradient Search
Therefore, in this paper, we propose a malicious prompt template construction method (\textbf{PromptAttack}) to probe the security performance of PLMs.
See What the Robot Can't See: Learning Cooperative Perception for Visual Navigation
We consider the problem of navigating a mobile robot towards a target in an unknown environment that is endowed with visual sensors, where neither the robot nor the sensors have access to global positioning information and only use first-person-view images.
What Matters for 3D Scene Flow Network
Our proposed model surpasses all existing methods by at least 38. 2% on FlyingThings3D dataset and 24. 7% on KITTI Scene Flow dataset for EPE3D metric.
Tackling Data Scarcity with Transfer Learning: A Case Study of Thickness Characterization from Optical Spectra of Perovskite Thin Films
Transfer learning increasingly becomes an important tool in handling data scarcity often encountered in machine learning.
SparseDet: Towards End-to-End 3D Object Detection
We believe this end-to-end paradigm of SparseDet will inspire new thinking on the sparsity of 3D object detection.
Emergence of Double-slit Interference by Representing Visual Space in Artificial Neural Networks
Artificial neural networks have realized incredible successes at image recognition, but the underlying mechanism of visual space representation remains a huge mystery.
A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection
Deep graph learning has achieved remarkable progresses in both business and scientific areas ranging from finance and e-commerce, to drug and advanced material discovery.
Side-aware Meta-Learning for Cross-Dataset Listener Diagnosis with Subjective Tinnitus
With the development of digital technology, machine learning has paved the way for the next generation of tinnitus diagnoses.
Disentangled and Side-aware Unsupervised Domain Adaptation for Cross-dataset Subjective Tinnitus Diagnosis
The side-aware unsupervised domain adaptation module adapts the class-irrelevant information as domain variance to a new dataset and excludes the variance to obtain the class-distill features for the new dataset classification.
FedSynth: Gradient Compression via Synthetic Data in Federated Learning
Model compression is important in federated learning (FL) with large models to reduce communication cost.
Neural-FST Class Language Model for End-to-End Speech Recognition
We propose Neural-FST Class Language Model (NFCLM) for end-to-end speech recognition, a novel method that combines neural network language models (NNLMs) and finite state transducers (FSTs) in a mathematically consistent framework.
SAR-GPA: SAR Generation Perturbation Algorithm
Finally, We design a series of simulation and experiment to verify the effectiveness of the adversarial examples and also the modulation sequences.
Diversity-boosted Generalization-Specialization Balancing for Zero-shot Learning
We further propose a differentiable dataset-level balance and update the weights in a linear annealing schedule to simulate network pruning and thus obtain the optimal structure for BSNet with dataset-level balance achieved.
EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection
Recently, fusing the LiDAR point cloud and camera image to improve the performance and robustness of 3D object detection has received more and more attention, as these two modalities naturally possess strong complementarity.
PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis
Learning intra-region contexts and inter-region relations are two effective strategies to strengthen feature representations for point cloud analysis.
Ranked #35 on
3D Point Cloud Classification
on ModelNet40
3D Hierarchical Refinement and Augmentation for Unsupervised Learning of Depth and Pose from Monocular Video
In this framework, the depth and pose estimations are hierarchically and mutually coupled to refine the estimated pose layer by layer.
Rethink, Revisit, Revise: A Spiral Reinforced Self-Revised Network for Zero-Shot Learning
Our framework outperforms state-of-the-art algorithms on four benchmark datasets in both zero-shot and generalized zero-shot settings, which demonstrates the effectiveness of spiral learning in learning generalizable and complex correlations.
Efficient 3D Deep LiDAR Odometry
An efficient 3D point cloud learning architecture, named EfficientLO-Net, for LiDAR odometry is first proposed in this paper.
An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot Learning
Zero-Shot Learning (ZSL) aims to transfer learned knowledge from observed classes to unseen classes via semantic correlations.
Opportunities for Machine Learning to Accelerate Halide Perovskite Commercialization and Scale-Up
While halide perovskites attract significant academic attention, examples of at-scale industrial production are still sparse.
Machine Learning with Knowledge Constraints for Process Optimization of Open-Air Perovskite Solar Cell Manufacturing
With a limited experimental budget of screening 100 process conditions, we demonstrated an efficiency improvement to 18. 5% as the best-in-our-lab device fabricated by RSPP, and we also experimentally found 10 unique process conditions to produce the top-performing devices of more than 17% efficiency, which is 5 times higher rate of success than the control experiments with pseudo-random Latin hypercube sampling.
Private Language Model Adaptation for Speech Recognition
Speech model adaptation is crucial to handle the discrepancy between server-side proxy training data and actual data received on local devices of users.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Model-Based Approach for Measuring the Fairness in ASR
The issue of fairness arises when the automatic speech recognition (ASR) systems do not perform equally well for all subgroups of the population.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Efficient Medical Image Segmentation Based on Knowledge Distillation
To deal with this problem, we propose an efficient architecture by distilling knowledge from well-trained medical image segmentation networks to train another lightweight network.
CONet: Channel Optimization for Convolutional Neural Networks
To solve this, we introduce an efficient dynamic scaling algorithm -- CONet -- that automatically optimizes channel sizes across network layers for a given CNN.
The Holy Grail of Multi-Robot Planning: Learning to Generate Online-Scalable Solutions from Offline-Optimal Experts
Many multi-robot planning problems are burdened by the curse of dimensionality, which compounds the difficulty of applying solutions to large-scale problem instances.
Motion Projection Consistency Based 3D Human Pose Estimation with Virtual Bones from Monocular Videos
Ablation studies demonstrate the effectiveness of the proposed inter-frame projection consistency constraints and intra-frame loop constraints.
Ranked #42 on
3D Human Pose Estimation
on Human3.6M
Learning To Identify Correct 2D-2D Line Correspondences on Sphere
In contrast, we propose the first approach suitable for both structured and unstructured scenes.
Impedance-optical Dual-modal Cell Culture Imaging with Learning-based Information Fusion
While Electrical Impedance Tomography (EIT) has found many biomedicine applications, a better resolution is needed to provide quantitative analysis for tissue engineering and regenerative medicine.
When and Why does a Model Fail? A Human-in-the-loop Error Detection Framework for Sentiment Analysis
Although deep neural networks have been widely employed and proven effective in sentiment analysis tasks, it remains challenging for model developers to assess their models for erroneous predictions that might exist prior to deployment.
When and Why a Model Fails? A Human-in-the-loop Error Detection Framework for Sentiment Analysis
Although deep neural networks have been widely employed and proven effective in sentiment analysis tasks, it remains challenging for model developers to assess their models for erroneous predictions that might exist prior to deployment.
THG: Transformer with Hyperbolic Geometry
In this work, we propose a novel Transformer with Hyperbolic Geometry (THG) model, which take the advantage of both Euclidean space and Hyperbolic space.
Benchmarking the Performance of Bayesian Optimization across Multiple Experimental Materials Science Domains
In the field of machine learning (ML) for materials optimization, active learning algorithms, such as Bayesian Optimization (BO), have been leveraged for guiding autonomous and high-throughput experimentation systems.
Accountable Error Characterization
Customers of machine learning systems demand accountability from the companies employing these algorithms for various prediction tasks.
Attribute-Modulated Generative Meta Learning for Zero-Shot Classification
The promising strategies for ZSL are to synthesize visual features of unseen classes conditioned on semantic side information and to incorporate meta-learning to eliminate the model's inherent bias towards seen classes.
Task Aligned Generative Meta-learning for Zero-shot Learning
Zero-shot learning (ZSL) refers to the problem of learning to classify instances from the novel classes (unseen) that are absent in the training set (seen).
Learning Icosahedral Spherical Probability Map Based on Bingham Mixture Model for Vanishing Point Estimation
Based on this map, we can detect all the VPs.
GAKP: GRU Association and Kalman Prediction for Multiple Object Tracking
Multiple Object Tracking (MOT) has been a useful yet challenging task in many real-world applications such as video surveillance, intelligent retail, and smart city.
Anchor-Based Spatio-Temporal Attention 3D Convolutional Networks for Dynamic 3D Point Cloud Sequences
Then, anchor-based 3D convolution is adopted to aggregate these anchors' features to the core points.
A Registration-aided Domain Adaptation Network for 3D Point Cloud Based Place Recognition
In the field of large-scale SLAM for autonomous driving and mobile robotics, 3D point cloud based place recognition has aroused significant research interest due to its robustness to changing environments with drastic daytime and weather variance.
ProMask: Probability Mask for Skeleton Detection
Detecting object skeletons in natural images presents challenging, due to varied object scales, the complexity of backgrounds and various noises.
PWCLO-Net: Deep LiDAR Odometry in 3D Point Clouds Using Hierarchical Embedding Mask Optimization
A novel 3D point cloud learning model for deep LiDAR odometry, named PWCLO-Net, using hierarchical embedding mask optimization is proposed in this paper.
Federated Marginal Personalization for ASR Rescoring
Our presented approach can overcome the limitations of federated fine-tuning and efficiently learn personalized NNLMs on devices.
Global Context-enhanced Graph Convolutional Networks for Document-level Relation Extraction
In this paper, we propose Global Context-enhanced Graph Convolutional Networks (GCGCN), a novel model which is composed of entities as nodes and context of entity pairs as edges between nodes to capture rich global context information of entities in a document.
End-to-End 3D Point Cloud Learning for Registration Task Using Virtual Correspondences
3D Point cloud registration is still a very challenging topic due to the difficulty in finding the rigid transformation between two point clouds with partial correspondences, and it's even harder in the absence of any initial estimation information.
3D Invisible Cloak
on person stealth attacks, and propose 3D transformations to generate 3D invisible cloak.
Spherical Interpolated Convolutional Network with Distance-Feature Density for 3D Semantic Segmentation of Point Clouds
In this paper, a spherical interpolated convolution operator is proposed to replace the traditional grid-shaped 3D convolution operator.
Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planning
Our Message-Aware Graph Attention neTwork (MAGAT) is based on a key-query-like mechanism that determines the relative importance of features in the messages received from various neighboring robots.
Learning of Long-Horizon Sparse-Reward Robotic Manipulator Tasks with Base Controllers
Deep Reinforcement Learning (DRL) enables robots to perform some intelligent tasks end-to-end.
Hierarchical Attention Learning of Scene Flow in 3D Point Clouds
In this paper, a novel hierarchical neural network with double attention is proposed for learning the correlation of point features in adjacent frames and refining scene flow from coarse to fine layer by layer.
DASGIL: Domain Adaptation for Semantic and Geometric-aware Image-based Localization
Long-Term visual localization under changing environments is a challenging problem in autonomous driving and mobile robotics due to season, illumination variance, etc.
Domain-invariant Similarity Activation Map Contrastive Learning for Retrieval-based Long-term Visual Localization
Visual localization is a crucial component in the application of mobile robot and autonomous driving.
EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection
In this paper, we aim at addressing two critical issues in the 3D detection task, including the exploitation of multiple sensors~(namely LiDAR point cloud and camera image), as well as the inconsistency between the localization and classification confidence.
Face to Purchase: Predicting Consumer Choices with Structured Facial and Behavioral Traits Embedding
We design a semi-supervised model based on a hierarchical embedding network to extract high-level features of consumers and to predict the top-$N$ purchase destinations of a consumer.
Spectrum-Guided Adversarial Disparity Learning
It has been a significant challenge to portray intraclass disparity precisely in the area of activity recognition, as it requires a robust representation of the correlation between subject-specific variation for each activity class.
Agglomerative Neural Networks for Multi-view Clustering
Conventional multi-view clustering methods seek for a view consensus through minimizing the pairwise discrepancy between the consensus and subviews.
Mobile Robot Path Planning in Dynamic Environments through Globally Guided Reinforcement Learning
Path planning for mobile robots in large dynamic environments is a challenging problem, as the robots are required to efficiently reach their given goals while simultaneously avoiding potential conflicts with other robots or dynamic objects.
Are You A Risk Taker? Adversarial Learning of Asymmetric Cross-Domain Alignment for Risk Tolerance Prediction
Most current studies on survey analysis and risk tolerance modelling lack professional knowledge and domain-specific models.
Statistical Testing on ASR Performance via Blockwise Bootstrap
A common question being raised in automatic speech recognition (ASR) evaluations is how reliable is an observed word error rate (WER) improvement comparing two ASR systems, where statistical hypothesis testing and confidence interval (CI) can be utilized to tell whether this improvement is real or only due to random chance.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
TANet: Robust 3D Object Detection from Point Clouds with Triple Attention
In this paper, we focus on exploring the robustness of the 3D object detection in point clouds, which has been rarely discussed in existing approaches.
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
Improving N-gram Language Models with Pre-trained Deep Transformer
Although n-gram language models (LMs) have been outperformed by the state-of-the-art neural LMs, they are still widely used in speech recognition due to its high efficiency in inference.
Teacher-Student Learning Paradigm for Tri-training: An Efficient Method for Unlabeled Data Exploitation
Given that labeled data is expensive to obtain in real-world scenarios, many semi-supervised algorithms have explored the task of exploitation of unlabeled data.
Retrieval-based Localization Based on Domain-invariant Feature Learning under Changing Environments
To retrieve a target image from the database, the query image is first encoded using the encoder belonging to the query domain to obtain a domain-invariant feature vector.
Adversarial Representation Learning for Robust Patient-Independent Epileptic Seizure Detection
Furthermore, to enhance the explainability, we develop an attention mechanism to automatically learn the importance of each EEG channels in the seizure diagnosis procedure.
DUT-BIM at MEDIQA 2019: Utilizing Transformer Network and Medical Domain-Specific Contextualized Representations for Question Answering
BioNLP 2019 proposes Question Answering (QA) task, which encourages the use of text mining technology to automatically judge whether a search result is an answer to the medical question.
Fast classification of small X-ray diffraction datasets using data augmentation and deep neural networks
We overcome the scarce data problem intrinsic to novel materials development by coupling a supervised machine learning approach with a model-agnostic, physics-informed data augmentation strategy using simulated data from the Inorganic Crystal Structure Database (ICSD) and experimental data.
SeqLPD: Sequence Matching Enhanced Loop-Closure Detection Based on Large-Scale Point Cloud Description for Self-Driving Vehicles
Place recognition and loop-closure detection are main challenges in the localization, mapping and navigation tasks of self-driving vehicles.
3D Object Detection Using Scale Invariant and Feature Reweighting Networks
On the other hand, our network obtains the useful features and suppresses the features with less information by a SENet module.
LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment Analysis
Point cloud based place recognition is still an open issue due to the difficulty in extracting local features from the raw 3D point cloud and generating the global descriptor, and it's even harder in the large-scale dynamic environments.
Fast and interpretable classification of small X-ray diffraction datasets using data augmentation and deep neural networks
X-ray diffraction (XRD) data acquisition and analysis is among the most time-consuming steps in the development cycle of novel thin-film materials.
Characterizing machine learning process: A maturity framework
For example, existing machine learning processes cannot address how to define business use cases for an AI application, how to convert business requirements from offering managers into data requirements for data scientists, and how to continuously improve AI applications in term of accuracy and fairness, and how to customize general purpose machine learning models with industry, domain, and use case specific data to make them more accurate for specific situations etc.
Generative Neural Networks for Anomaly Detection in Crowded Scenes
Security surveillance is critical to social harmony and people's peaceful life.
Ranked #3 on
Abnormal Event Detection In Video
on UBI-Fights
Fostering User Engagement: Rhetorical Devices for Applause Generation Learnt from TED Talks
One problem that every presenter faces when delivering a public discourse is how to hold the listeners' attentions or to keep them involved.
See the Near Future: A Short-Term Predictive Methodology to Traffic Load in ITS
Based on the Gaussian distribution of traffic flow, a hybrid model with a Bayesian learning algorithm is developed which can effectively expand the application scenarios of SARIMA.
Learning Nonparametric Forest Graphical Models with Prior Information
We present a framework for incorporating prior information into nonparametric estimation of graphical models.
Graphical Exponential Screening
In high dimensions we propose and analyze an aggregation estimator of the precision matrix for Gaussian graphical models.
Blossom Tree Graphical Models
We combine the ideas behind trees and Gaussian graphical models to form a new nonparametric family of graphical models.
An Aggregation Method for Sparse Logistic Regression
We also analyze a published genome-wide case-control dataset to further evaluate the usefulness of the aggregation method in multilocus association mapping.
