Search Results for author:
Found 276 papers, 124 papers with code
Dual Adversarial Network for Deep Active Learning
In this paper, we investigate the overlapping problem of recent uncertainty-based approaches and propose to alleviate the issue by taking representativeness into consideration.
Large-Scale Few-Shot Learning via Multi-Modal Knowledge Discovery
It is a challenging problem since (1) the identifying process is susceptible to over-fitting with limited samples of an object, and (2) the sample imbalance between a base (known knowledge) category and a novel category is easy to bias the recognition results.
Exclusivity-Consistency Regularized Knowledge Distillation for Face Recognition
Knowledge distillation is an effective tool to compress large pre-trained Convolutional Neural Networks (CNNs) or their ensembles into models applicable to mobile and embedded devices.
SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning
In this paper, we present a novel efficient query selection and preference-guided exploration method, called SENIOR, which could select the meaningful and easy-to-comparison behavior segment pairs to improve human feedback-efficiency and accelerate policy learning with the designed preference-guided intrinsic rewards.
Restoring Gaussian Blurred Face Images for Deanonymization Attacks
The key intuition is to leverage a generative model's memorization effect and approximate the inverse function of Gaussian blur for face restoration.
ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization
Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of Large Language Models (LLMs).
MF2Summ: Multimodal Fusion for Video Summarization with Temporal Alignment
Segment importance, location, and center-ness are predicted, followed by key shot selection using Non-Maximum Suppression (NMS) and the Kernel Temporal Segmentation (KTS) algorithm.
Mutual-Supervised Learning for Sequential-to-Parallel Code Translation
MSL consists of two models, a Translator and a Tester.
MiniCPM4: Ultra-Efficient LLMs on End Devices
Specifically, in terms of model architecture, we propose InfLLM v2, a trainable sparse attention mechanism that accelerates both prefilling and decoding phases for long-context processing.
Trajectory Optimization for UAV-Based Medical Delivery with Temporal Logic Constraints and Convex Feasible Set Collision Avoidance
This paper addresses the problem of trajectory optimization for unmanned aerial vehicles (UAVs) performing time-sensitive medical deliveries in urban environments.
A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings
Specifically, A*-Thought can improve the performance of QwQ-32B by 2. 39$\times$ with low-budget and reduce the length of the output token by nearly 50% with high-budget.
AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage
Building on this idea, we propose AutoReproduce, a multi-agent framework capable of automatically reproducing experiments described in research papers in an end-to-end manner.
PCDCNet: A Surrogate Model for Air Quality Forecasting with Physical-Chemical Dynamics and Constraints
Air quality forecasting (AQF) is critical for public health and environmental management, yet remains challenging due to the complex interplay of emissions, meteorology, and chemical transformations.
Monocle: Hybrid Local-Global In-Context Evaluation for Long-Text Generation with Uncertainty-Based Active Learning
Moreover, we introduce a hybrid in-context learning approach that leverages human annotations to enhance the performance of both local and global evaluations.
A Survey of LLM $\times$ DATA
The integration of large language model (LLM) and data management (DATA) is rapidly redefining both domains.
Shadows in the Attention: Contextual Perturbation and Representation Drift in the Dynamics of Hallucination in LLMs
Hallucinations -- plausible yet erroneous outputs -- remain a critical barrier to reliable deployment of large language models (LLMs).
From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora
Continued pretraining and instruction tuning on large-scale multilingual data have proven to be effective in scaling large language models (LLMs) to low-resource languages.
DD-Ranking: Rethinking the Evaluation of Dataset Distillation
In recent years, dataset distillation has provided a reliable solution for data compression, where models trained on the resulting smaller synthetic datasets achieve performance comparable to those trained on the original datasets.
Patient-Specific Dynamic Digital-Physical Twin for Coronary Intervention Training: An Integrated Mixed Reality Approach
We developed cardiac output analysis and virtual angiography systems, implemented guidewire 3D reconstruction using binocular stereo vision, and evaluated the system through angiography validation and CABG training applications.
Endo-CLIP: Progressive Self-Supervised Pre-training on Raw Colonoscopy Records
Pre-training on image-text colonoscopy records offers substantial potential for improving endoscopic image analysis, but faces challenges including non-informative background images, complex medical terminology, and ambiguous multi-lesion descriptions.
Avoid Recommending Out-of-Domain Items: Constrained Generative Recommendation with LLMs
Large Language Models (LLMs) have shown promise for generative recommender systems due to their transformative capabilities in user interaction.
Innovative Integration of 4D Cardiovascular Reconstruction and Hologram: A New Visualization Tool for Coronary Artery Bypass Grafting Planning
Objective: To develop and evaluate a dynamic cardiovascular holographic visualization tool for preoperative CABG planning.
DiffUMI: Training-Free Universal Model Inversion via Unconditional Diffusion for Face Recognition
It surpasses state-of-the-art attacks by 15. 5% and 9. 82% in success rate on standard and privacy-preserving face recognition systems, respectively.
RT-DATR:Real-time Unsupervised Domain Adaptive Detection Transformer with Adversarial Feature Learning
Building on RT-DETR as our base detector, we first introduce a local object-level feature alignment module to significantly enhance the feature representation of domain invariance during object transfer.
LLM$\times$MapReduce-V2: Entropy-Driven Convolutional Test-Time Scaling for Generating Long-Form Articles from Extremely Long Resources
Long-form generation is crucial for a wide range of practical applications, typically categorized into short-to-long and long-to-long generation.
Improving Harmful Text Detection with Joint Retrieval and External Knowledge
Harmful text detection has become a crucial task in the development and deployment of large language models, especially as AI-generated content continues to expand across digital platforms.
Benchmarking Federated Machine Unlearning methods for Tabular Data
Machine unlearning, which enables a model to forget specific data upon request, is increasingly relevant in the era of privacy-centric machine learning, particularly within federated learning (FL) environments.
Why Stop at One Error? Benchmarking LLMs as Data Science Code Debuggers for Multi-Hop and Multi-Bug Errors
To address this gap, we introduce DSDBench: the Data Science Debugging Benchmark, the first benchmark for systematic evaluation of LLMs on multi-hop error tracing and multi-bug detection in data science code debugging.
Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation
To mine fine-grained knowledge from visual features, our VC module first proposes Static Visual Calibration (SVC) to propagate fine-grained knowledge in a non-parametric manner.
RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing
Recent advances in self-supervised learning for Vision Transformers (ViTs) have fueled breakthroughs in remote sensing (RS) foundation models.
TLA: Tactile-Language-Action Model for Contact-Rich Manipulation
Significant progress has been made in vision-language models.
From Pixels to Trajectory: Universal Adversarial Example Detection via Temporal Imprints
Recognizing the distinct nature of loss between adversarial and clean examples, we exploit this temporal imprint for AE detection by proposing TRAIT (TRaceable Adversarial temporal trajectory ImprinTs).
NeuGrasp: Generalizable Neural Surface Reconstruction with Background Priors for Material-Agnostic Object Grasp Detection
Robotic grasping in scenes with transparent and specular objects presents great challenges for methods relying on accurate depth information.
Towards Universal Learning-based Model for Cardiac Image Reconstruction: Summary of the CMRxRecon2024 Challenge
In addition, through a detailed analysis of the results submitted to the challenge, we have also made several findings, including: 1) adaptive prompt-learning embedding is an effective means for achieving strong generalization in reconstruction models; 2) enhanced data consistency based on physics-informed networks is also an effective pathway toward a universal model; 3) traditional evaluation metrics have limitations when assessing ground-truth references with moderate or lower image quality, highlighting the need for subjective evaluation methods.
Time-Varying Coronary Artery Deformation: A Dynamic Skinning Framework for Surgical Training
Purpose: This study proposes a novel anatomically-driven dynamic modeling framework for coronary arteries using skeletal skinning weights computation, aiming to achieve precise control over vessel deformation while maintaining real-time performance for surgical simulation applications.
Robust Polyp Detection and Diagnosis through Compositional Prompt-Guided Diffusion Models
Diffusion models have emerged as a promising solution for generating synthetic polyp images, but the image generation process in current models mainly relies on segmentation masks as the condition, limiting their ability to capture the full clinical context.
Exploring the Impact of Personality Traits on LLM Bias and Toxicity
The findings demonstrate the sensitivity of all three models to HEXACO personality traits and, more importantly, a consistent variation in the biases, negative sentiment and toxicity of their output.
GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning
Large Language Models (LLMs) fine-tuning technologies have achieved remarkable results.
CoDiff: Conditional Diffusion Model for Collaborative 3D Object Detection
Experimental study on both simulated and real-world datasets demonstrates that the proposed framework CoDiff consistently outperforms existing relevant methods in terms of the collaborative object detection performance, and exhibits highly desired robustness when the pose and delay information of agents is with high-level noise.
DCAD-2000: A Multilingual Dataset across 2000+ Languages with Data Cleaning as Anomaly Detection
The rapid development of multilingual large language models (LLMs) highlights the need for high-quality, diverse, and clean multilingual datasets.
Vertical Federated Continual Learning via Evolving Prototype Knowledge
Vertical Federated Learning (VFL) has garnered significant attention as a privacy-preserving machine learning framework for sample-aligned feature federation.
The establishment of static digital humans and the integration with spinal models
Next, we align the real spine model reconstructed from CT images with the standard skeletal model.
DAMO: Data- and Model-aware Alignment of Multi-modal LLMs
Direct Preference Optimization (DPO) has shown effectiveness in aligning multi-modal large language models (MLLM) with human preferences.
LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information
Finally, we apply step-level DPO using the collected stepwise preference pairs.
Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignment
To address these issues, we propose the Multi-Domain Graph Foundation Model (MDGFM), a unified framework that aligns and leverages cross-domain topological information to facilitate robust knowledge transfer.
Process Reinforcement through Implicit Rewards
While dense rewards also offer an appealing choice for the reinforcement learning (RL) of LLMs since their fine-grained rewards have the potential to address some inherent issues of outcome rewards, such as training efficiency and credit assignment, this potential remains largely unrealized.
MQuant: Unleashing the Inference Potential of Multimodal Large Language Models via Full Static Quantization
In this paper, we propose MQuant, a post-training quantization (PTQ) framework designed to tackle the unique challenges of multimodal large language models (MLLMs).
Accelerating Diffusion Transformer via Error-Optimized Cache
Existing caching methods accelerate generation by reusing DiT features from the previous time step and skipping calculations in the next, but they tend to locate and cache low-error modules without focusing on reducing caching-induced errors, resulting in a sharp decline in generated content quality when increasing caching intensity.
ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation
: (1) Low executability and poor restoration of chart details in the generated code and (2) Lack of large-scale and diverse training data.
CoDe: Communication Delay-Tolerant Multi-Agent Collaboration via Dual Alignment of Intent and Timeliness
This paper first defines two communication delay settings in MARL and emphasizes their harm to collaboration.
Enhancing Adversarial Transferability with Checkpoints of a Single Model's Training
Adversarial attacks threaten the integrity of deep neural networks (DNNs), particularly in high-stakes applications.
MambaVO: Deep Visual Odometry Based on Sequential Matching Refinement and Training Smoothing
To address this challenge, this paper proposes MambaVO, which conducts robust initialization, Mamba-based sequential matching refinement, and smoothed training to enhance the matching quality and improve the pose estimation in deep visual odometry.
Feature Alignment-Based Knowledge Distillation for Efficient Compression of Large Language Models
This study proposes a knowledge distillation algorithm based on large language models and feature alignment, aiming to effectively transfer the knowledge of large pre-trained models into lightweight student models, thereby reducing computational costs while maintaining high model performance.
Dust to Tower: Coarse-to-Fine Photo-Realistic Scene Reconstruction from Sparse Uncalibrated Images
To refine the 3D model at novel viewpoints, we propose a Confidence Aware Depth Alignment (CADA) module to refine the coarse depth maps by aligning their confident parts with estimated depths by a Mono-depth model.
Linguistics-Vision Monotonic Consistent Network for Sign Language Production
Sign Language Production (SLP) aims to generate sign videos corresponding to spoken language sentences, where the conversion of sign Glosses to Poses (G2P) is the key step.
FedGA: Federated Learning with Gradient Alignment for Error Asymmetry Mitigation
Federated learning (FL) triggers intra-client and inter-client class imbalance, with the latter compared to the former leading to biased client updates and thus deteriorating the distributed models.
Understanding Knowledge Hijack Mechanism in In-context Learning through Associative Memory
In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks without fine-tuning by leveraging contextual information provided within a prompt.
MoRe: Class Patch Attention Needs Regularization for Weakly Supervised Semantic Segmentation
To this end, we first view the attention as a novel directed graph and propose the Graph Category Representation module to implicitly regularize the interaction among class-patch entities.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Medical Manifestation-Aware De-Identification
Face de-identification (DeID) has been widely studied for common scenes, but remains under-researched for medical scenes, mostly due to the lack of large-scale patient face datasets.
Parameter Estimation based Automatic Modulation Recognition for Radio Frequency Signal
However, current automatic identification methods require the input of key parameters such as the carrier frequency, which is necessary to convert the radio frequency (RF) to a base-band signal before it can be used for identification.
Optimizing Multi-Task Learning for Enhanced Performance in Large Language Models
This study aims to explore the performance improvement method of large language models based on GPT-4 under the multi-task learning framework and conducts experiments on two tasks: text classification and automatic summary generation.
World-Consistent Data Generation for Vision-and-Language Navigation
Vision-and-Language Navigation (VLN) is a challenging task that requires an agent to navigate through photorealistic environments following natural-language instructions.
Rethinking the initialization of Momentum in Federated Learning with Heterogeneous Data
However, we spot a problem in the traditional cumulation of the momentum which is suboptimal in the Federated Learning systems.
KBAlign: Efficient Self Adaptation on Specific Knowledge Bases
Although retrieval-augmented generation (RAG) remains essential for knowledge-based question answering (KBQA), current paradigms face critical challenges under specific domains.
A Combined Encoder and Transformer Approach for Coherent and High-Quality Text Generation
This research introduces a novel text generation model that combines BERT's semantic interpretation strengths with GPT-4's generative capabilities, establishing a high standard in generating coherent, contextually accurate language.
Transfer Learning Guided Noise Reduction for Automatic Modulation Classification
The numerical results show that the proposed noise reduction network achieves an accuracy improvement of over 20\% in low SNR scenarios, and the TNR-AMC framework can improve the classification accuracy under unstable SNRs.
Advanced RAG Models with Graph Structures: Optimizing Complex Knowledge Reasoning and Text Generation
This study proposes a scheme to process graph structure data by combining graph neural network (GNN), so that the model can capture the complex relationship between entities, thereby improving the knowledge consistency and reasoning ability of the generated text.
MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning
Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA have significantly improved the adaptation of LLMs to downstream tasks in a resource-efficient manner.
Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting
Vision-language models, such as CLIP, have shown impressive generalization capacities when using appropriate text descriptions.
Building A Coding Assistant via the Retrieval-Augmented Language Model
Specifically, it consists of a code structure aware retriever (CONAN-R) and a dual-view code representation-based retrieval-augmented generation model (CONAN-G).
Automated Genre-Aware Article Scoring and Feedback Using Large Language Models
This paper focuses on the development of an advanced intelligent article scoring system that not only assesses the overall quality of written work but also offers detailed feature-based scoring tailored to various article genres.
Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs
These experiments reveal that while most current models are robust against the "lost in the middle" issue, there exist significant biases related to the spacing of relevant information pieces.
RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards
Our experiments on various knowledge-intensive tasks demonstrate that DDR significantly outperforms the SFT method, particularly for LLMs with smaller-scale parameters that depend more on the retrieved knowledge.
LLM$\times$MapReduce: Simplified Long-Sequence Processing using Large Language Models
The proposed LLM$\times$MapReduce framework splits the entire document into several chunks for LLMs to read and then aggregates the intermediate answers to produce the final output.
Retriever-and-Memory: Towards Adaptive Note-Enhanced Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) mitigates issues of the factual errors and hallucinated outputs generated by Large Language Models (LLMs) in open-domain question-answering tasks (OpenQA) via introducing external knowledge.
FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image Classification
Unlike few-shot learning methods in natural images that can leverage the labels of each image, existing few-shot WSI classification methods only utilize a small number of fine-grained labels or weakly supervised slide labels for training in order to avoid expensive fine-grained annotation.
Space-time 2D Gaussian Splatting for Accurate Surface Reconstruction under Complex Dynamic Scenes
To tackle the dynamic contents and the occlusions in complex scenes, we present a space-time 2D Gaussian Splatting approach.
PGN: The RNN's New Successor is Effective for Long-Range Time Series Forecasting
The other branch employs patches to capture short-term information and aggregate the global representation of the series.
Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning
Moreover, existing methods primarily rely on contrastive learning to maximize mutual information across different graphs, limiting them to multiplex graph redundant scenarios and failing to capture view-unique task-relevant information.
Towards Ground-truth-free Evaluation of Any Segmentation in Medical Images
We name this model EvanySeg (Evaluation of Any Segmentation in Medical Images).
A Personalised 3D+t Mesh Generative Model for Unveiling Normal Heart Dynamics
To this end, we developed a novel conditional generative model, MeshHeart, to learn the distribution of cardiac shape and motion patterns.
Differentiable Collision-Supervised Tooth Arrangement Network with a Decoupling Perspective
Therefore, we propose DTAN, a differentiable collision-supervised tooth arrangement network, decoupling predicting tasks and feature modeling.
Enabling Real-Time Conversations with Minimal Training Costs
To address this limitation, researchers have proposed duplex models.
RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervision
However, compared to dense supervision detectors like the YOLO series, the Hungarian matching provides much sparser supervision, leading to insufficient model training and difficult to achieve optimal results.
GAZEploit: Remote Keystroke Inference Attack by Gaze Estimation from Avatar Views in VR/MR Devices
The advent and growing popularity of Virtual Reality (VR) and Mixed Reality (MR) solutions have revolutionized the way we interact with digital platforms.
Low carbon optimal scheduling of integrated energy system considering waste heat utilization under the coordinated operation of incineration power plant and P2G
In order to improve energy utilization and reduce carbon emissions, this paper presents a comprehensive energy system economic operation strategy of Incineration power plant Power-to-gas (P2G) with waste heat recovery.
Configurable Foundation Models: Building LLMs from a Modular Perspective
We first formalize modules into emergent bricks - functional neuron partitions that emerge during the pre-training phase, and customized bricks - bricks constructed via additional post-training to improve the capabilities and knowledge of LLMs.
Video-based Analysis Reveals Atypical Social Gaze in People with Autism Spectrum Disorder
In this study, we present a quantitative and comprehensive analysis of social gaze in people with autism spectrum disorder (ASD).
TIMotion: Temporal and Interactive Framework for Efficient Human-Human Motion Generation
For temporal modeling, the single-person-based methods concatenate two people into a single one directly, while the separate modeling-based methods skip the modeling of interaction sequences.
GSLAMOT: A Tracklet and Query Graph-based Simultaneous Locating, Mapping, and Multiple Object Tracking System
GSLAMOT utilizes camera and LiDAR multimodal information as inputs and divides the representation of the dynamic scene into a semantic map for representing the static environment, a trajectory of the ego-agent, and an online maintained Tracklet Graph (TG) for tracking and predicting the 3D poses of the detected mobile objects.
A Multi-task Adversarial Attack Against Face Authentication
In this paper, we propose a multi-task adversarial attack algorithm called MTADV that are adaptable for multiple users or systems.
Improving Global Parameter-sharing in Physically Heterogeneous Multi-agent Reinforcement Learning with Unified Action Space
To further improve the training of extra UAS parameters, we introduce a Cross-Group Inverse (CGI) loss to predict other groups' agent policies with the trajectory information.
COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis
In this paper, we introduce DEBUGEVAL, a comprehensive benchmark for evaluating the debugging abilities of LLMs by emulating the multi-stage human debugging process.
RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework
However, evaluating the effectiveness of RAG systems in specialized scenarios remains challenging due to the high costs of data construction and the lack of suitable evaluation metrics.
RoCo:Robust Collaborative Perception By Iterative Object Matching and Pose Adjustment
However, in collaborative perception, the quality of object detection based on a modality is highly sensitive to the relative pose errors among the agents.
Selective Vision-Language Subspace Projection for Few-shot CLIP
Vision-language models such as CLIP are capable of mapping the different modality data into a unified feature space, enabling zero/few-shot inference by measuring the similarity of given images and texts.
Towards Automated Data Sciences with Natural Language and SageCopilot: Practices and Lessons Learned
While the field of NL2SQL has made significant advancements in translating natural language instructions into executable SQL scripts for data querying and processing, achieving full automation within the broader data science pipeline - encompassing data querying, analysis, visualization, and reporting - remains a complex challenge.
Rethinking Visual Content Refinement in Low-Shot CLIP Adaptation
However, these adaptation methods are usually operated on the global view of an input image, and thus biased perception of partial local details of the image.
Model Inversion Attacks Through Target-Specific Conditional Diffusion Models
To alleviate these issues, leveraging on diffusion models' remarkable synthesis capabilities, we propose Diffusion-based Model Inversion (Diff-MI) attacks.
EndoFinder: Online Image Retrieval for Explainable Colorectal Polyp Diagnosis
To overcome this limitation, we introduce EndoFinder, a content-based image retrieval framework to find the 'digital twin' polyp in the reference database given a newly detected polyp.
Releasing Malevolence from Benevolence: The Menace of Benign Data on Machine Unlearning
Our evaluation demonstrates that unlearning this benign data, comprising no more than 1% of the total training data, can reduce model accuracy by up to 50%.
CMRxRecon2024: A Multi-Modality, Multi-View K-Space Dataset Boosting Universal Machine Learning for Accelerated Cardiac MRI
To the best of our knowledge, the CMRxRecon2024 dataset is the largest and most protocal-diverse publicly available cardiac k-space dataset.
An Empirical Study on the Fairness of Foundation Models for Multi-Organ Image Segmentation
We test state-of-the-art foundation models for medical image segmentation, including the original SAM, medical SAM and SAT models, to evaluate segmentation efficacy across different demographic groups and identify disparities.
Scale-Translation Equivariant Network for Oceanic Internal Solitary Wave Localization
In this paper, we propose to inject prior knowledge to achieve a strong and efficient learner.
On the Combination of AI and Wireless Technologies: 3GPP Standardization Progress
Combing Artificial Intelligence (AI) and wireless communication technologies has become one of the major technologies trends towards 2030.
Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models
Motivated by the long-tail distribution of singular values in the delta weights, we propose a delta quantization approach using mixed-precision.
MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning
It is observed that the minor matrix corresponds to the noisy or long-tail information, while the principal matrix contains important knowledge.
Improving Segment Anything on the Fly: Auxiliary Online Learning and Adaptive Fusion for Medical Image Segmentation
We employ rectified annotations to perform online learning, with the aim of improving the segmentation quality of SA on medical images.
Hierarchical Space-Time Attention for Micro-Expression Recognition
Specifically, we first process ME video frames and special frames or data parallelly by our cascaded Unimodal Space-Time Attention (USTA) to establish connections between subtle facial movements and specific facial areas.
Micro Expression Recognition
Micro-Expression Recognition
+1
Exploiting ChatGPT for Diagnosing Autism-Associated Language Disorders and Identifying Distinct Features
Diagnosing language disorders associated with autism is a complex challenge, often hampered by the subjective nature and variability of traditional assessment methods.
Exploring Speech Pattern Disorders in Autism using Machine Learning
Diagnosing autism spectrum disorder (ASD) by identifying abnormal speech patterns from examiner-patient dialogues presents significant challenges due to the subtle and diverse manifestations of speech-related symptoms in affected individuals.
The 8th AI City Challenge
The eighth AI City Challenge highlighted the convergence of computer vision and artificial intelligence in areas like retail, warehouse settings, and Intelligent Traffic Systems (ITS), presenting significant research opportunities.
Tackling Ambiguity from Perspective of Uncertainty Inference and Affinity Diversification for Weakly Supervised Semantic Segmentation
When activating class objects, we argue that the false activation stems from the bias to the ambiguous regions during the feature extraction.
The state-of-the-art in Cardiac MRI Reconstruction: Results of the CMRxRecon Challenge in MICCAI 2023
To address this issue, we organized the Cardiac MRI Reconstruction Challenge (CMRxRecon) in 2023, in collaboration with the 26th International Conference on MICCAI.
Boosting Few-Shot Learning via Attentive Feature Regularization
Few-shot learning (FSL) based on manifold regularization aims to improve the recognition capacity of novel objects with limited training samples by mixing two samples from different categories with a blending factor.
Technical Report: Masked Skeleton Sequence Modeling for Learning Larval Zebrafish Behavior Latent Embeddings
In this report, we introduce a novel self-supervised learning method for extracting latent embeddings from behaviors of larval zebrafish.
SoK: Can Trajectory Generation Combine Privacy and Utility?
This work focuses on the systematisation of the state-of-the-art generative models for trajectories in the context of the proposed framework.
Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation
In this work, we devise a 'Separate and Conquer' scheme SeCo to tackle this issue from dimensions of image space and feature space.
Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression
It finetunes the compression plugin module and uses the representations of gist tokens to emulate the raw prompts in the vanilla language model.
From Text to CQL: Bridging Natural Language and Corpus Search Engine
This paper presents the first text-to-CQL task that aims to automate the translation of natural language into CQL.
OMGEval: An Open Multilingual Generative Evaluation Benchmark for Large Language Models
We evaluate several representative multilingual LLMs on the proposed OMGEval, which we believe will provide a valuable reference for the community to further understand and improve the multilingual capability of LLMs.
$\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens
Processing and reasoning over long contexts is crucial for many practical applications of Large Language Models (LLMs), such as document comprehension and agent construction.
ActiveRAG: Autonomously Knowledge Assimilation and Accommodation through Retrieval-Augmented Agents
Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to leverage external knowledge, enhancing their performance on knowledge-intensive tasks.
Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages
While large language models (LLMs) have been pre-trained on multilingual corpora, their performance still lags behind in most languages compared to a few resource-rich languages.
MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization
Scientific data visualization plays a crucial role in research by enabling the direct display of complex information and assisting researchers in identifying implicit patterns.
LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks
Most prior works on LoRA combination primarily rely on task-level weights for each involved LoRA, making different examples and tokens share the same LoRA weights.
OneBit: Towards Extremely Low-bit Large Language Models
Model quantification uses low bit-width values to represent the weight matrices of existing models to be quantized, which is a promising approach to reduce both storage and computational overheads of deploying highly anticipated LLMs.
UltraLink: An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset
Different from previous works that simply translate English instructions, we consider both the language-specific and language-agnostic abilities of LLMs.
Learning with Mixture of Prototypes for Out-of-Distribution Detection
To tackle these issues, we propose PrototypicAl Learning with a Mixture of prototypes (PALM) which models each class with multiple prototypes to capture the sample diversities, and learns more faithful and compact samples embeddings to enhance OOD detection.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+1
LegalDuet: Learning Fine-grained Representations for Legal Judgment Prediction via a Dual-View Contrastive Learning
In this paper, we propose LegalDuet, which continuously pretrains language models to learn a more tailored embedding space for representing legal cases.
Stream Query Denoising for Vectorized HD Map Construction
This paper introduces the Stream Query Denoising (SQD) strategy as a novel approach for temporal modeling in high-definition map (HD-map) construction.
Graph Elimination Networks
Graph Neural Networks (GNNs) are widely applied across various domains, yet they perform poorly in deep layers.
SQA-SAM: Segmentation Quality Assessment for Medical Images Utilizing the Segment Anything Model
Segmentation quality assessment (SQA) plays a critical role in the deployment of a medical image based AI system.
GraphGuard: Detecting and Counteracting Training Data Misuse in Graph Neural Networks
These limitations call for an effective and comprehensive solution that detects and mitigates data misuse without requiring exact training data while respecting the proprietary nature of such data.
Transferring Modality-Aware Pedestrian Attentive Learning for Visible-Infrared Person Re-identification
Visible-infrared person re-identification (VI-ReID) aims to search the same pedestrian of interest across visible and infrared modalities.
Enhancing Recipe Retrieval with Foundation Models: A Data Augmentation Perspective
Leveraging on the remarkable capabilities of foundation models (i. e., Llama2 and SAM), we propose to augment recipe and food image by extracting alignable information related to the counterpart.
Building Category Graphs Representation with Spatial and Temporal Attention for Visual Navigation
To this end, an agent needs to 1) learn a piece of certain knowledge about the relations of object categories in the world during training and 2) look for the target object based on the pre-learned object category relations and its moving trajectory in the current unseen environment.
A Reliable Representation with Bidirectional Transition Model for Visual Reinforcement Learning Generalization
Visual reinforcement learning has proven effective in solving control tasks with high-dimensional observations.
INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair
INTERVENOR prompts Large Language Models (LLMs) to play distinct roles during the code repair process, functioning as both a Code Learner and a Code Teacher.
Ranked #32 on
Code Generation
on MBPP
TSP-Transformer: Task-Specific Prompts Boosted Transformer for Holistic Scene Understanding
Holistic scene understanding includes semantic segmentation, surface normal estimation, object boundary detection, depth estimation, etc.
Understanding Parameter Saliency via Extreme Value Theory
Furthermore, we show that the existing parameter saliency method exhibits a bias against the depth of layers in deep neural networks.
Breaking of brightness consistency in optical flow with a lightweight CNN network
Modifying the typical brightness consistency of the optical flow method to the convolutional feature consistency yields the light-robust hybrid optical flow method.
VFedMH: Vertical Federated Learning for Training Multiple Heterogeneous Models
Then the passive party, who owns only features of the sample, injects the blinding factor into the local embedding and sends it to the active party.
Knowledge Extraction and Distillation from Large-Scale Image-Text Colonoscopy Records Leveraging Large Language and Vision Models
EndoKED automates the transformation of raw colonoscopy records into image datasets with pixel-level annotation.
Action Recognition Utilizing YGAR Dataset
The scarcity of high quality actions video data is a bottleneck in the research and application of action recognition.
Natural Language Models for Data Visualization Utilizing nvBench Dataset
Translation of natural language into syntactically correct commands for data visualization is an important application of natural language models and could be leveraged to many different tasks.
CMRxRecon: An open cardiac MRI dataset for the competition of accelerated image reconstruction
However, a limitation of CMR is its slow imaging speed, which causes patient discomfort and introduces artifacts in the images.
RR-CP: Reliable-Region-Based Conformal Prediction for Trustworthy Medical Image Classification
Conformal prediction (CP) generates a set of predictions for a given test sample such that the prediction set almost always contains the true label (e. g., 99. 5\% of the time).
Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf
Communication games, which we refer to as incomplete information games that heavily depend on natural language communication, hold significant research value in fields such as economics, social science, and artificial intelligence.
SamDSK: Combining Segment Anything Model with Domain-Specific Knowledge for Semi-Supervised Learning in Medical Image Segmentation
Our new method is iterative and consists of two main stages: (1) segmentation model training; (2) expanding the labeled set by using the trained segmentation model, an unlabeled set, SAM, and domain-specific knowledge.
A Unified Query-based Paradigm for Camouflaged Instance Segmentation
Due to the high similarity between camouflaged instances and the background, the recently proposed camouflaged instance segmentation (CIS) faces challenges in accurate localization and instance segmentation.
Pluggable Neural Machine Translation Models via Memory-augmented Adapters
Although neural machine translation (NMT) models perform well in the general domain, it remains rather challenging to control their generation behavior to satisfy the requirement of different users.
Synthetic Demographic Data Generation for Card Fraud Detection Using GANs
This study can help improve the cognition of synthetic data and further explore the application of synthetic data generation in card fraud detection.
Segmentation and Tracking of Vegetable Plants by Exploiting Vegetable Shape Feature for Precision Spray of Agricultural Robots
Regarding the robust tracking of vegetable plants, to solve the challenging problem of associating vegetables with similar color and texture in consecutive images, in this paper, a novel method of Multiple Object Tracking and Segmentation (MOTS) is proposed for instance segmentation and tracking of multiple vegetable plants.
MCTS: A Multi-Reference Chinese Text Simplification Dataset
We hope to build a basic understanding of Chinese text simplification through the foundational work and provide references for future research.
AirBirds: A Large-scale Challenging Dataset for Bird Strike Prevention in Real-world Airports
To advance the research and practical solutions for bird strike prevention, in this paper, we present a large-scale challenging dataset AirBirds that consists of 118, 312 time-series images, where a total of 409, 967 bounding boxes of flying birds are manually, carefully annotated.
IDLS: Inverse Depth Line based Visual-Inertial SLAM
Using this compact line presentation, Inverse Depth Line SLAM (IDLS) is proposed to track the line features in SLAM in an accurate and efficient way.
Input Augmentation with SAM: Boosting Medical Image Segmentation with Segmentation Foundation Model
Thus, how to utilize such a large foundation model for medical image segmentation is an emerging research target.
Video-based Contrastive Learning on Decision Trees: from Action Recognition to Autism Diagnosis
How can we teach a computer to recognize 10, 000 different actions?
The 7th AI City Challenge
The AI City Challenge's seventh edition emphasizes two domains at the intersection of computer vision and artificial intelligence - retail business and Intelligent Traffic Systems (ITS) - that have considerable untapped potential.
CamDiff: Camouflage Image Augmentation via Diffusion Model
Specifically, we leverage the latent diffusion model to synthesize salient objects in camouflaged scenes, while using the zero-shot image classification ability of the Contrastive Language-Image Pre-training (CLIP) model to prevent synthesis failures and ensure the synthesized object aligns with the input prompt.
Bi-directional Distribution Alignment for Transductive Zero-Shot Learning
It is well-known that zero-shot learning (ZSL) can suffer severely from the problem of domain shift, where the true and learned data distributions for the unseen classes do not match.
Toward a Geometric Theory of Manifold Untangling
It has been hypothesized that the ventral stream processing for object recognition is based on a mechanism called cortically local subspace untangling.
Towards Domain Generalization for Multi-view 3D Object Detection in Bird-Eye-View
Based on the covariate shift assumption, we find that the gap mainly attributes to the feature distribution of BEV, which is determined by the quality of both depth estimation and 2D image's feature representation.
Memory-aided Contrastive Consensus Learning for Co-salient Object Detection
To learn better group consensus, we propose the Group Consensus Aggregation Module (GCAM) to abstract the common features of each image group; meanwhile, to make the consensus representation more discriminative, we introduce the Memory-based Contrastive Module (MCM), which saves and updates the consensus of images from different groups in a queue of memories.
Dynamic Graph Neural Network with Adaptive Edge Attributes for Air Quality Predictions
Previous GCNs-based methods usually require providing spatial correlation graph structure of observation sites in advance.
Deep-Learning Tool for Early Identifying Non-Traumatic Intracranial Hemorrhage Etiology based on CT Scan
Conclusions: The proposed deep learning algorithms can be an effective tool for early identification of hemorrhage etiologies based on NCCT scans.
CHeart: A Conditional Spatio-Temporal Generative Model for Cardiac Anatomy
Two key questions in cardiac image analysis are to assess the anatomy and motion of the heart from images; and to understand how they are associated with non-imaging clinical factors such as gender, age and diseases.
Boosting Whole Slide Image Classification from the Perspectives of Distribution, Correlation and Magnification
However, there are still three important issues that have not been fully addressed: (1) positive bags with a low positive instance ratio are prone to the influence of a large number of negative instances; (2) the correlation between local and global features of pathology images has not been fully modeled; and (3) there is a lack of effective information interaction between different magnifications.
Learning from Noisy Data for Semi-Supervised 3D Object Detection
To this end, we propose NoiseDet, a simple yet effective framework for semi-supervised 3D object detection.
EndoBoost: a plug-and-play module for false positive suppression during computer-aided polyp detection in real-world colonoscopy (with dataset)
In addition, the released dataset can be used to perform 'stress' tests on established detection systems and encourages further research toward robust and reliable computer-aided endoscopic image analysis.
Source-free Depth for Object Pop-out
In this work, we adapt such depth inference models for object segmentation using the objects' "pop-out" prior in 3D.
DeepTaster: Adversarial Perturbation-Based Fingerprinting to Identify Proprietary Dataset Use in Deep Neural Networks
In this study, we introduce DeepTaster, a novel DNN fingerprinting technique, to address scenarios where a victim's data is unlawfully used to build a suspect model.
DETRDistill: A Universal Knowledge Distillation Framework for DETR-families
Next, we propose a target-aware feature distillation to help the student model learn from the object-centric features of the teacher model.
Multitask Learning for Improved Late Mechanical Activation Detection of Heart from Cine DENSE MRI
With a newly introduced auxiliary LMA region classification sub-network, our proposed model shows more robustness to the complex pattern cause by myocardial scar, significantly eliminates their negative effects in LMA detection, and in turn improves the performance of scar classification.
Joint Deep Learning for Improved Myocardial Scar Detection from Cardiac MRI
Automated identification of myocardial scar from late gadolinium enhancement cardiac magnetic resonance images (LGE-CMR) is limited by image noise and artifacts such as those related to motion and partial volume effect.
The Extreme Cardiac MRI Analysis Challenge under Respiratory Motion (CMRxMotion)
The quality of cardiac magnetic resonance (CMR) imaging is susceptible to respiratory motion artifacts.
Generative Modelling of the Ageing Heart with Cross-Sectional Imaging and Clinical Data
Understanding the morphological and functional changes of the heart during ageing is a key scientific question, the answer to which will help us define important risk factors of cardiovascular disease and monitor disease progression.
Improved post-hoc probability calibration for out-of-domain MRI segmentation
In image segmentation, well-calibrated probabilities allow radiologists to identify regions where model-predicted segmentations are unreliable.
Parameterization of Cross-Token Relations with Relative Positional Encoding for Vision MLP
They use token-mixing layers to capture cross-token interactions, as opposed to the multi-head self-attention mechanism used by Transformers.
TANet: Transformer-based Asymmetric Network for RGB-D Salient Object Detection
We employ the powerful feature extraction capability of Transformer (PVTv2) to extract global semantic information from RGB data and design a lightweight CNN backbone (LWDepthNet) to extract spatial structure information from depth data without pre-training.
Trichomonas Vaginalis Segmentation in Microscope Images
Trichomoniasis is a common infectious disease with high incidence caused by the parasite Trichomonas vaginalis, increasing the risk of getting HIV in humans if left untreated.
Boundary-Guided Camouflaged Object Detection
Camouflaged object detection (COD), segmenting objects that are elegantly blended into their surroundings, is a valuable yet challenging task.
Generative Myocardial Motion Tracking via Latent Space Exploration with Biomechanics-informed Prior
In contrast to most existing approaches which impose explicit generic regularization such as smoothness, in this work we propose a novel method that can implicitly learn an application-specific biomechanics-informed prior and embed it into a neural network-parameterized transformation model.
Suggestive Annotation of Brain MR Images with Gradient-guided Sampling
We evaluate the framework on two different brain image analysis tasks, namely brain tumour segmentation and whole brain segmentation.
A Template-based Method for Constrained Neural Machine Translation
In this work, we propose a template-based method that can yield results with high translation quality and match accuracy and the inference speed of our method is comparable with unconstrained NMT models.
Understanding and Mitigating the Uncertainty in Zero-Shot Translation
Zero-shot translation is a promising direction for building a comprehensive multilingual neural machine translation~(MNMT) system.
DcnnGrasp: Towards Accurate Grasp Pattern Recognition with Adaptive Regularizer Learning
The task of grasp pattern recognition aims to derive the applicable grasp types of an object according to the visual information.
InvNorm: Domain Generalization for Object Detection in Gastrointestinal Endoscopy
Therefore, to address the generalization problem in GI(Gastrointestinal) endoscopy, we propose a multi-domain GI dataset and a light, plug-in block called InvNorm(Invertible Normalization), which could achieve a better generalization performance in any structure.
Long-term Spatio-temporal Forecasting via Dynamic Multiple-Graph Attention
To address these issues, we construct new graph models to represent the contextual information of each node and the long-term spatio-temporal data dependency structure.
The 6th AI City Challenge
The four challenge tracks of the 2022 AI City Challenge received participation requests from 254 teams across 27 countries.
Attention in Attention: Modeling Context Correlation for Efficient Video Classification
Attention mechanisms have significantly boosted the performance of video classification neural networks thanks to the utilization of perspective contexts.
Synthetic Distracted Driving (SynDD2) dataset for analyzing distracted behaviors and various gaze zones of a driver
This article presents a synthetic distracted driving (SynDD2 - a continuum of SynDD1) dataset for machine learning models to detect and analyze drivers' various distracted behavior and different gaze zones.
Towards Web Phishing Detection Limitations and Mitigation
However, with an average of 10K phishing links reported per hour to platforms such as PhishTank and VirusTotal (VT), the deficiencies of such ML-based solutions are laid bare.
A Roadmap for Big Model
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
Integrating Vectorized Lexical Constraints for Neural Machine Translation
In this work, we propose to open this black box by directly integrating the constraints into NMT models.
High-resolution Iterative Feedback Network for Camouflaged Object Detection
Spotting camouflaged objects that are visually assimilated into the background is tricky for both object detection algorithms and humans who are usually confused or cheated by the perfectly intrinsic similarities between the foreground objects and the background surroundings.
