Search Results for author:
Found 95 papers, 28 papers with code
RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems
Role-playing systems powered by large language models (LLMs) have become increasingly influential in emotional communication applications.
EFA-YOLO: An Efficient Feature Attention Model for Fire and Flame Detection
Compared with existing mainstream models (e. g., YOLOv5, YOLOv8, YOLOv9, and YOLOv10), EFA-YOLO exhibits a significant enhancement in detection accuracy (mAP) and inference speed, with model parameter amount is reduced by 94. 6 and the inference speed is improved by 88 times.
Real-Time Dynamic Scale-Aware Fusion Detection Network: Take Road Damage Detection as an example
Experimental results on the UAV-PDD2023 public dataset show that our model RT-DSAFDet achieves a mAP50 of 54. 2%, which is 11. 1% higher than that of YOLOv10-m, an efficient variant of the latest real-time object detection model YOLOv10, while the amount of parameters is reduced to 1. 8M and FLOPs to 4. 6G, with a decreased by 88% and 93%, respectively.
DAPONet: A Dual Attention and Partially Overparameterized Network for Real-Time Road Damage Detection
Current road damage detection methods, relying on manual inspections or sensor-mounted vehicles, are inefficient, limited in coverage, and often inaccurate, especially for minor damages, leading to delays and safety hazards.
Sliced Maximal Information Coefficient: A Training-Free Approach for Image Quality Assessment Enhancement
Full-reference image quality assessment (FR-IQA) models generally operate by measuring the visual differences between a degraded image and its reference.
ByCAN: Reverse Engineering Controller Area Network (CAN) Messages from Bit to Byte Level
As the primary standard protocol for modern cars, the Controller Area Network (CAN) is a critical research target for automotive cybersecurity threats and autonomous applications.
ECG-Chat: A Large ECG-Language Model for Cardiac Disease Diagnosis
Additionally, expanding existing datasets, we constructed a 19k ECG diagnosis dataset and a 25k multi-turn dialogue dataset for training and fine-tuning ECG-Chat, which provides professional diagnostic and conversational capabilities.
Fishers Harvest Parallel Unlearning in Inherited Model Networks
A key enabler is the new Unified Model Inheritance Graph (UMIG), which captures the inheritance using a Directed Acyclic Graph (DAG). Central to our framework is the new Fisher Inheritance Unlearning (FIUn) algorithm, which utilizes the Fisher Information Matrix (FIM) from initial unlearning models to pinpoint impacted parameters in inherited models.
HoME: Hierarchy of Multi-Gate Experts for Multi-Task Learning at Kuaishou
(3) Expert Underfitting: In our services, we have dozens of behavior tasks that need to be predicted, but we find that some data-sparse prediction tasks tend to ignore their specific-experts and assign large weights to shared-experts.
3D Weakly Supervised Semantic Segmentation with 2D Vision-Language Guidance
In this paper, we propose 3DSS-VLG, a weakly supervised approach for 3D Semantic Segmentation with 2D Vision-Language Guidance, an alternative approach that a 3D model predicts dense-embedding for each point which is co-embedded with both the aligned image and text spaces from the 2D vision-language model.
NegativePrompt: Leveraging Psychology for Large Language Models Enhancement via Negative Emotional Stimuli
The results are revealing: NegativePrompt markedly enhances the performance of LLMs, evidenced by relative improvements of 12. 89% in Instruction Induction tasks and 46. 25% in BIG-Bench tasks.
Delayed Bottlenecking: Alleviating Forgetting in Pre-trained Graph Neural Networks
Pre-training GNNs to extract transferable knowledge and apply it to downstream tasks has become the de facto standard of graph representation learning.
FACTUAL: A Novel Framework for Contrastive Learning Based Robust SAR Image Classification
FACTUAL consists of two components: (1) Differing from existing works, a novel perturbation scheme that incorporates realistic physical adversarial attacks (such as OTSA) to build a supervised adversarial pre-training network.
Weakly-Supervised 3D Scene Graph Generation via Visual-Linguistic Assisted Pseudo-labeling
However, previous 3D scene graph generation methods utilize a fully supervised learning manner and require a large amount of entity-level annotation data of objects and relations, which is extremely resource-consuming and tedious to obtain.
Semi-Instruct: Bridging Natural-Instruct and Self-Instruct for Code Large Language Models
Presently, two dominant paradigms for collecting tuning data are natural-instruct (human-written) and self-instruct (automatically generated).
Surgment: Segmentation-enabled Semantic Search and Creation of Visual Question and Feedback to Support Video-Based Surgery Learning
The segmentation pipeline enables functionalities to create visual questions and feedback desired by surgeons from a formative study.
BlockFUL: Enabling Unlearning in Blockchained Federated Learning
Unlearning in Federated Learning (FL) presents significant challenges, as models grow and evolve with complex inheritance relationships.
3DPFIX: Improving Remote Novices' 3D Printing Troubleshooting through Human-AI Collaboration
While troubleshooting plays an essential part of 3D printing, the process remains challenging for many remote novices even with the help of well-developed online sources, such as online troubleshooting archives and online community help.
A Survey on Data Augmentation in Large Model Era
Leveraging large models, these data augmentation techniques have outperformed traditional approaches.
PepGB: Facilitating peptide drug discovery via graph neural networks
In summary, our proposed frameworks can serve as potent tools to facilitate peptide early drug discovery.
On Robust Wasserstein Barycenter: The Model and Algorithm
Firstly, we improve efficiency through model reducing; we reduce RWB as an augmented Wasserstein barycenter problem, which works for both fixed-RWB and free-RWB.
Weakly-Supervised 3D Visual Grounding based on Visual Linguistic Alignment
During the inference stage, the learned text-3D correspondence will help us ground the text queries to the 3D target objects even without 2D images.
Rankitect: Ranking Architecture Search Battling World-class Engineers at Meta Scale
In industry system, such as ranking system in Meta, it is unclear whether NAS algorithms from the literature can outperform production baselines because of: (1) scale - Meta ranking systems serve billions of users, (2) strong baselines - the baselines are production models optimized by hundreds to thousands of world-class engineers for years since the rise of deep learning, (3) dynamic baselines - engineers may have established new and stronger baselines during NAS search, and (4) efficiency - the search pipeline must yield results quickly in alignment with the productionization life cycle.
Expanding the Vocabulary of BERT for Knowledge Base Construction
To address this, we present Vocabulary Expandable BERT for knowledge base construction, which expand the language model's vocabulary while preserving semantic embeddings for newly added words.
Ranked #1 on
Knowledge Base Population
on LM-KBC 2023
PhotoVerse: Tuning-Free Image Customization with Text-to-Image Diffusion Models
Personalized text-to-image generation has emerged as a powerful and sought-after tool, empowering users to create customized images based on their specific concepts and prompts.
AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Pose
We present AvatarVerse, a stable pipeline for generating expressive high-quality 3D avatars from nothing but text descriptions and pose guidance.
Multi-modal Learning based Prediction for Disease
From the dataset, we quantitatively analyze and select clinical metadata that most contribute to NAFLD prediction.
A Secure Aggregation for Federated Learning on Long-Tailed Data
As a distributed learning, Federated Learning (FL) faces two challenges: the unbalanced distribution of training data among participants, and the model attack by Byzantine nodes.
CSCLog: A Component Subsequence Correlation-Aware Log Anomaly Detection Method
To this end, we propose CSCLog, a Component Subsequence Correlation-Aware Log anomaly detection method, which not only captures the sequential dependencies in subsequences, but also models the implicit correlations of subsequences.
A Survey on Evaluation of Large Language Models
Large language models (LLMs) are gaining increasing popularity in both academia and industry, owing to their unprecedented performance in various applications.
Research on an improved Conformer end-to-end Speech Recognition Model with R-Drop Structure
To address the issue of poor generalization ability in end-to-end speech recognition models within deep learning, this study proposes a new Conformer-based speech recognition model called "Conformer-R" that incorporates the R-drop structure.
Research on Named Entity Recognition in Improved transformer with R-Drop structure
To enhance the generalization ability of the model and improve the effectiveness of the transformer for named entity recognition tasks, the XLNet-Transformer-R model is proposed in this paper.
Automated 3D Pre-Training for Molecular Property Prediction
Next, to automatically fuse these three generative tasks, we design a surrogate metric using the \textit{total energy} to search for weight distribution of the three pretext task since total energy corresponding to the quality of 3D conformer. Extensive experiments on 2D molecular graphs are conducted to demonstrate the accuracy, efficiency and generalization ability of the proposed 3D PGT compared to various pre-training baselines.
DialogVCS: Robust Natural Language Understanding in Dialogue System Upgrade
In the constant updates of the product dialogue systems, we need to retrain the natural language understanding (NLU) model as new data from the real users would be merged into the existent data accumulated in the last updates.
Blockchained Federated Learning for Internet of Things: A Comprehensive Survey
The demand for intelligent industries and smart services based on big data is rising rapidly with the increasing digitization and intelligence of the modern world.
Point Transformer For Coronary Artery Labeling
Coronary CT angiography (CCTA) scans are widely used for diagnosis of coronary artery diseases.
Cross-Modal Retrieval with Partially Mismatched Pairs
On the one hand, our method only utilizes the negative information which is much less likely false compared with the positive information, thus avoiding the overfitting issue to PMPs.
Contrastive Learning
Cross-modal retrieval with noisy correspondence
+2
Correspondence-Free Domain Alignment for Unsupervised Cross-Domain Image Retrieval
Thanks to the ISS and CCA, our method could encode the discrimination into the domain-invariant embedding space for unsupervised cross-domain image retrieval.
Graph-Free Learning in Graph-Structured Data: A More Efficient and Accurate Spatiotemporal Learning Perspective
In this paper, with extensive and deep-going experiments, we comprehensively analyze existing spatiotemporal graph learning models and reveal that extracting adjacency matrices with carefully design strategies, which are viewed as the key of enhancing performance on graph learning, are largely ineffective.
SwiftAvatar: Efficient Auto-Creation of Parameterized Stylized Character on Arbitrary Avatar Engines
To this end, we propose SwiftAvatar, a novel avatar auto-creation framework that is evidently superior to previous works.
IronForge: An Open, Secure, Fair, Decentralized Federated Learning
Federated learning (FL) provides an effective machine learning (ML) architecture to protect data privacy in a distributed manner.
Local and Global Logit Adjustments for Long-Tailed Learning
LGLA consists of two core components: a Class-aware Logit Adjustment (CLA) strategy and an Adaptive Angular Weighted (AAW) loss.
DialogQAE: N-to-N Question Answer Pair Extraction from Customer Service Chatlog
Harvesting question-answer (QA) pairs from customer service chatlog in the wild is an efficient way to enrich the knowledge base for customer service chatbots in the cold start or continuous integration scenarios.
DualNER: A Dual-Teaching framework for Zero-shot Cross-lingual Named Entity Recognition
We present DualNER, a simple and effective framework to make full use of both annotated source language corpus and unlabeled target language text for zero-shot cross-lingual named entity recognition (NER).
LAD-RCNN:A Powerful Tool for Livestock Face Detection and Normalization
However, there is no study on normalizing of the animal face image with arbitrary directions.
Deep Evidential Learning with Noisy Correspondence for Cross-Modal Retrieval
However, it will unavoidably introduce noise (i. e., mismatched pairs) into training data, dubbed noisy correspondence.
Ranked #2 on
Text-based Person Retrieval with Noisy Correspondence
on RSTPReid
(using extra training data)
Cross-modal retrieval with noisy correspondence
Retrieval
+1
Semi-automatic Data Annotation System for Multi-Target Multi-Camera Vehicle Tracking
However, according to our investigation, the lacking of datasets focusing on real-world application scenarios limits the further improvements for current learning-based MTMCT models.
Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentation
To tackle with this issue, this paper proposes an Expansion and Shrinkage scheme based on the offset learning in the deformable convolution, to sequentially improve the recall and precision of the located object in the two respective stages.
Weakly Supervised Semantic Segmentation via Progressive Patch Learning
"Progressive Patch Learning" further extends the feature destruction and patch learning to multi-level granularities in a progressive manner.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classification
To address this issue, we propose a novel Adaptive Meta-learner via Gradient Similarity (AMGS) method to improve the model generalization ability to a new task.
Gaze Estimation Approach Using Deep Differential Residual Network
We propose a differential residual model (DRNet) combined with a new loss function to make use of the difference information of two eye images.
Graph Property Prediction on Open Graph Benchmark: A Winning Solution by Graph Neural Architecture Search
Aiming at two molecular graph datasets and one protein association subgraph dataset in OGB graph classification task, we design a graph neural network framework for graph classification task by introducing PAS(Pooling Architecture Search).
Towards Process-Oriented, Modular, and Versatile Question Generation that Meets Educational Needs
NLP-powered automatic question generation (QG) techniques carry great pedagogical potential of saving educators' time and benefiting student learning.
Predictive and Contrastive: Dual-Auxiliary Learning for Recommendation
To explore recommendation-specific auxiliary tasks, we first quantitatively analyze the heterogeneous interaction data and find a strong positive correlation between the interactions and the number of user-item paths induced by meta-paths.
Boundary Corrected Multi-scale Fusion Network for Real-time Semantic Segmentation
Image semantic segmentation aims at the pixel-level classification of images, which has requirements for both accuracy and speed in practical application.
Distortion-Aware Loop Filtering of Intra 360^o Video Coding with Equirectangular Projection
In this paper, we propose a distortion-aware loop filtering model to improve the performance of intra coding for 360$^o$ videos projected via equirectangular projection (ERP) format.
LighTN: Light-weight Transformer Network for Performance-overhead Tradeoff in Point Cloud Downsampling
Compared with traditional task-irrelevant downsampling methods, task-oriented neural networks have shown improved performance in point cloud downsampling range.
On the predictability in reversible steganography
The core strength of neural networks is the ability to render accurate predictions for a bewildering variety of data.
A Semantic Web Technology Index
In this paper, we propose an SW technology index to standardize the development for ensuring that the work of SW technology is designed well and to quantitatively evaluate the quality of the work in SW technology.
Graph Neural Networks for Double-Strand DNA Breaks Prediction
Double-strand DNA breaks (DSBs) are a form of DNA damage that can cause abnormal chromosomal rearrangements.
URetinex-Net: Retinex-Based Deep Unfolding Network for Low-Light Image Enhancement
Retinex model-based methods have shown to be effective in layer-wise manipulation with well-designed priors for low-light image enhancement.
Robust and Precise Facial Landmark Detection by Self-Calibrated Pose Attention Network
We show that by integrating the BALI fields and SCPA model into a novel self-calibrated pose attention network, more facial prior knowledge can be learned and the detection accuracy and robustness of our method for faces with large poses and heavy occlusions have been improved.
Multi-Faceted Hierarchical Multi-Task Learning for a Large Number of Tasks with Multi-dimensional Relations
For example, when using MTL to model various user behaviors in RS, if we differentiate new users and new items from old ones, there will be a cartesian product style increase of tasks with multi-dimensional relations.
A Feature Consistency Driven Attention Erasing Network for Fine-Grained Image Retrieval
To handle these two issues, we propose a feature consistency driven attention erasing network (FCAENet) for fine-grained image retrieval.
DRAN: Detailed Region-Adaptive Normalization for Conditional Image Synthesis
To evaluate the effectiveness and show the general use of our method, we conduct a set of experiments on makeup transfer and semantic image synthesis.
Fast Point Voxel Convolution Neural Network with Selective Feature Fusion for Point Cloud Semantic Segmentation
Each layer has two parallel branches, namely the voxel branch and the point branch.
Joint Estimation and Inference for Multi-Experiment Networks of High-Dimensional Point Processes
Modern high-dimensional point process data, especially those from neuroscience experiments, often involve observations from multiple conditions and/or experiments.
SPNet: Multi-Shell Kernel Convolution for Point Cloud Semantic Segmentation
Experimental results show that SPConv is effective in local shape encoding, and our SPNet is able to achieve top-ranking performances in semantic segmentation tasks.
Causal Discovery in High-Dimensional Point Process Networks with Hidden Nodes
Thanks to technological advances leading to near-continuous time observations, emerging multivariate point process data offer new opportunities for causal discovery.
FCM: A Fine-grained Comparison Model for Multi-turn Dialogue Reasoning
Furthermore, the consistency signals between each candidate and the speaker's own history are considered to drive a model to prefer a candidate that is logically consistent with the speaker's history logic.
TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios
Object detection on drone-captured scenarios is a recent popular task.
Deep Learning for Predictive Analytics in Reversible Steganography
Given that reversibility is governed independently by the coding module, we narrow our focus to the incorporation of neural networks into the analytics module, which serves the purpose of predicting pixel intensities and a pivotal role in determining capacity and imperceptibility.
Global Wheat Head Dataset 2021: more diversity to improve the benchmarking of wheat head localization methods
We now release a new version of the Global Wheat Head Detection (GWHD) dataset in 2021, which is bigger, more diverse, and less noisy than the 2020 version.
On the Optimality of Nuclear-norm-based Matrix Completion for Problems with Smooth Non-linear Structure
Originally developed for imputing missing entries in low rank, or approximately low rank matrices, matrix completion has proven widely effective in many problems where there is no reason to assume low-dimensional linear structure in the underlying matrix, as would be imposed by rank constraints.
Integrating Subgraph-aware Relation and DirectionReasoning for Question Answering
Question Answering (QA) models over Knowledge Bases (KBs) are capable of providing more precise answers by utilizing relation information among entities.
Attention Models for Point Clouds in Deep Learning: A Survey
Recently, the advancement of 3D point clouds in deep learning has attracted intensive research in different application domains such as computer vision and robotic tasks.
Periodic repeating fast radio bursts: interaction between a magnetized neutron star and its planet in an eccentric orbit
Fast radio bursts (FRBs) are mysterious transient phenomena.
High Energy Astrophysical Phenomena
Modelling Long-distance Node Relations for KBQA with Global Dynamic Graph
The structural information of Knowledge Bases (KBs) has proven effective to Question Answering (QA).
Open Domain Question Answering based on Text Enhanced Knowledge Graph with Hyperedge Infusion
The incompleteness of knowledge base (KB) is a vital factor limiting the performance of question answering (QA).
Value Cards: An Educational Toolkit for Teaching Social Impacts of Machine Learning through Deliberation
In this paper, we present Value Card, an educational toolkit to inform students and practitioners of the social impacts of different machine learning models via deliberation.
Statistical Inference for Networks of High-Dimensional Point Processes
The key ingredient for this inference procedure is a new concentration inequality on the first- and second-order statistics for integrated stochastic processes, which summarize the entire history of the process.
Automate Obstructive Sleep Apnea Diagnosis Using Convolutional Neural Networks
Identifying sleep problem severity from overnight polysomnography (PSG) recordings plays an important role in diagnosing and treating sleep disorders such as the Obstructive Sleep Apnea (OSA).
Hybrid Attention for Automatic Segmentation of Whole Fetal Head in Prenatal Ultrasound Volumes
In this paper, we propose the first fully-automated solution to segment the whole fetal head in US volumes.
A survey of statistical learning techniques as applied to inexpensive pediatric Obstructive Sleep Apnea data
Pediatric obstructive sleep apnea affects an estimated 1-5% of elementary-school aged children and can lead to other detrimental health problems.
Exploiting Local and Global Structure for Point Cloud Semantic Segmentation with Contextual Point Representations
In this paper, we propose one novel model for point cloud semantic segmentation, which exploits both the local and global structures within the point cloud based on the contextual point representations.
Agent with Warm Start and Active Termination for Plane Localization in 3D Ultrasound
In this study, we propose a novel reinforcement learning (RL) framework to automatically localize fetal brain standard planes in 3D US.
Joint Segmentation and Landmark Localization of Fetal Femur in Ultrasound Volumes
In this paper, we propose an effective framework for simultaneous segmentation and landmark localization in prenatal ultrasound volumes.
A Survey of Automatic Generation of Source Code Comments: Algorithms and Techniques
Finally, we summarize some future directions for advancing the techniques of automatic generation of code comments and the quality assessment of comments.
Software Engineering
High Sensitivity Snapshot Spectrometer Based on Deep Network Unmixing
In this paper, we present a convolution neural network based method to recover the light intensity distribution from the overlapped dispersive spectra instead of adding an extra light path to capture it directly for the first time.
DeepSquare: Boosting the Learning Power of Deep Convolutional Neural Networks with Elementwise Square Operators
In this paper, we pursue very efficient neural network modules which can significantly boost the learning power of deep convolutional neural networks with negligible extra computational cost.
Combating Uncertainty with Novel Losses for Automatic Left Atrium Segmentation
In this paper, we propose a fully-automated framework to segment left atrium in gadolinium-enhanced MR volumes.
Coordinating Collaborative Chat in Massive Open Online Courses
An earlier study of a collaborative chat intervention in a Massive Open Online Course (MOOC) identified negative effects on attrition stemming from a requirement for students to be matched with exactly one partner prior to beginning the activity.
Fast Landmark Subspace Clustering
Kernel methods obtain superb performance in terms of accuracy for various machine learning tasks since they can effectively extract nonlinear relations.
Spectral Convergence Rate of Graph Laplacian
Laplacian Eigenvectors of the graph constructed from a data set are used in many spectral manifold learning algorithms such as diffusion maps and spectral clustering.
Riemannian Multi-Manifold Modeling
This paper advocates a novel framework for segmenting a dataset in a Riemannian manifold $M$ into clusters lying around low-dimensional submanifolds of $M$.
