Search Results for author:
Found 91 papers, 32 papers with code
Enhancing Systematic Reviews with Large Language Models: Using GPT-4 and Kimi
This research delved into GPT-4 and Kimi, two Large Language Models (LLMs), for systematic reviews.
Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables
To address these challenges, we propose Pan-LUT, a novel learnable look-up table (LUT) framework for pan-sharpening that strikes a balance between performance and computational efficiency for high-resolution remote sensing images.
OCRT: Boosting Foundation Models in the Open World with Object-Concept-Relation Triad
Although foundation models (FMs) claim to be powerful, their generalization ability significantly decreases when faced with distribution shifts, weak supervision, or malicious attacks in the open world.
UPME: An Unsupervised Peer Review Framework for Multimodal Large Language Model Evaluation
Multimodal Large Language Models (MLLMs) have emerged to tackle the challenges of Visual Question Answering (VQA), sparking a new research focus on conducting objective evaluations of these models.
Bridging Synthetic-to-Real Gaps: Frequency-Aware Perturbation and Selection for Single-shot Multi-Parametric Mapping Reconstruction
Data-centric artificial intelligence (AI) has remarkably advanced medical imaging, with emerging methods using synthetic data to address data scarcity while introducing synthetic-to-real gaps.
Beyond Single-Value Metrics: Evaluating and Enhancing LLM Unlearning with Cognitive Diagnosis
Due to the widespread use of LLMs and the rising critical ethical and safety concerns, LLM unlearning methods have been developed to remove harmful knowledge and undesirable capabilities.
Exploiting Point-Language Models with Dual-Prompts for 3D Anomaly Detection
Additionally, based on the characteristics of point cloud data, we propose a pseudo 3D anomaly generation method (Ano3D) to improve the model's detection capabilities in an unsupervised setting.
Preference Leakage: A Contamination Problem in LLM-as-a-judge
All of these findings imply that preference leakage is a widespread and challenging problem in the area of LLM-as-a-judge.
STAMPsy: Towards SpatioTemporal-Aware Mixed-Type Dialogues for Psychological Counseling
Online psychological counseling dialogue systems are trending, offering a convenient and accessible alternative to traditional in-person therapy.
Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment
While compositional approaches that combine separate language and image models show a 111% improvement over unified models at the holistic level, their performance remains suboptimal at both block and image levels.
Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?
To address this, we introduce TrustSim, an evaluation dataset covering 10 CSS-related topics, to systematically investigate the reliability of the LLM simulation.
AutoBench-V: Can Large Vision-Language Models Benchmark Themselves?
Large Vision-Language Models (LVLMs) have become essential for advancing the integration of visual and linguistic information.
Single-Timescale Multi-Sequence Stochastic Approximation Without Fixed Point Smoothness: Theories and Applications
Stochastic approximation (SA) that involves multiple coupled sequences, known as multiple-sequence SA (MSSA), finds diverse applications in the fields of signal processing and machine learning.
Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge
LLM-as-a-Judge has been widely utilized as an evaluation method in various benchmarks and served as supervised rewards in model training.
Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors
As diffusion models are sensitive to noise, diffusion priors are introduced to achieve high-performance noise suppression.
Bootstrap Segmentation Foundation Model under Distribution Shift via Object-Centric Learning
Foundation models have made incredible strides in achieving zero-shot or few-shot generalization, leveraging prompt engineering to mimic the problem-solving approach of human intelligence.
Mixstyle-Entropy: Domain Generalization with Causal Intervention and Perturbation
In this paper, we propose a novel and holistic framework based on causality, named InPer, designed to enhance model generalization by incorporating causal intervention during training and causal perturbation during testing.
Can Large Language Models Automatically Jailbreak GPT-4V?
In our study, we introduce AutoJailbreak, an innovative automatic jailbreak technique inspired by prompt optimization.
Unity in Diversity: Multi-expert Knowledge Confrontation and Collaboration for Generalizable Vehicle Re-identification
To solve this complex and common problem, this paper proposes the two-stage Multi-expert Knowledge Confrontation and Collaboration (MiKeCoCo) method, which incorporates multiple experts with unique perspectives into Contrastive Language-Image Pretraining (CLIP) and fully leverages high-level semantic knowledge for comprehensive feature representation.
UniGen: A Unified Framework for Textual Dataset Generation Using Large Language Models
Large Language Models (LLMs) such as GPT-4 and Llama3 have significantly impacted various fields by enabling high-quality synthetic data generation and reducing dependence on expensive human-generated datasets.
Quantifying AI Psychology: A Psychometrics Benchmark for Large Language Models
Inspired by psychometrics, this paper presents a framework for investigating psychology in LLMs, including psychological dimension identification, assessment dataset curation, and assessment with results validation.
1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators?
This paper introduces a method to enhance the multilingual performance of LLMs by aggregating knowledge from diverse languages.
Jailbreaking Large Language Models Through Alignment Vulnerabilities in Out-of-Distribution Settings
Recently, Large Language Models (LLMs) have garnered significant attention for their exceptional natural language processing capabilities.
GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding
We evaluate the capabilities of current state-of-the-art MLLMs, including Image LLMs and Video LLMs, in understanding various types of GUI content, especially dynamic and sequential content.
HonestLLM: Toward an Honest and Helpful Large Language Model
Subsequently, we present two approaches to augmenting honesty and helpfulness in LLMs: a training-free enhancement and a fine-tuning-based improvement.
Optimization-based Prompt Injection Attack to LLM-as-a-Judge
In this work, we propose JudgeDeceiver, an optimization-based prompt injection attack to LLM-as-a-Judge.
Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
Sora is a text-to-video generative AI model, released by OpenAI in February 2024.
I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBench
Do large language models (LLMs) exhibit any forms of awareness similar to humans?
LLM-as-a-Coauthor: Can Mixed Human-Written and Machine-Generated Text Be Detected?
With the rapid development and widespread application of Large Language Models (LLMs), the use of Machine-Generated Text (MGT) has become increasingly common, bringing with it potential risks, especially in terms of quality and integrity in fields like news, education, and science.
Ranked #2 on
Binary text classification
on MixSet (Binary)
TrustLLM: Trustworthiness in Large Language Models
This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions.
AlignBench: Benchmarking Chinese Alignment of Large Language Models
Alignment has become a critical step for instruction-tuned Large Language Models (LLMs) to become helpful assistants.
FakeGPT: Fake News Generation, Explanation and Detection of Large Language Models
The rampant spread of fake news has adversely affected society, resulting in extensive research on curbing its spread.
Activate and Reject: Towards Safe Domain Generalization under Category Shift
Albeit the notable performance on in-domain test points, it is non-trivial for deep neural networks to attain satisfactory accuracy when deploying in the open world, where novel domains and object classes often occur.
MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use
However, in scenarios where LLMs serve as intelligent agents, as seen in applications like AutoGPT and MetaGPT, LLMs are expected to engage in intricate decision-making processes that involve deciding whether to employ a tool and selecting the most suitable tool(s) from a collection of available tools to fulfill user requests.
CSPRD: A Financial Policy Retrieval Dataset for Chinese Stock Market
In recent years, great advances in pre-trained language models (PLMs) have sparked considerable research focus and achieved promising performance on the approach of dense passage retrieval, which aims at retrieving relative passages from massive corpus with given questions.
SRCD: Semantic Reasoning with Compound Domains for Single-Domain Generalized Object Detection
In this paper, we introduce Semantic Reasoning with Compound Domains (SRCD) for Single-DGOD.
Ranked #4 on
Robust Object Detection
on DWD
TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Models
Through the implementation of TrustGPT, this research aims to enhance our understanding of the performance of conversation generation models and promote the development of language models that are more ethical and socially responsible.
MASNet: A Robust Deep Marine Animal Segmentation Network
Specifically, we design a new data augmentation strategy to randomly change the degradation and camouflage attributes of the original objects.
Ranked #3 on
Image Segmentation
on RMAS
DeID-GPT: Zero-shot Medical Text De-Identification by GPT-4
The digitization of healthcare has facilitated the sharing and re-using of medical data but has also raised concerns about confidentiality and privacy.
A Deep Learning Approach for SAR Tomographic Imaging of Forested Areas
Synthetic aperture radar tomographic imaging reconstructs the three-dimensional reflectivity of a scene from a set of coherent acquisitions performed in an interferometric configuration.
Learning a Simple Low-Light Image Enhancer From Paired Low-Light Instances
Those solutions, however, often fail in revealing image details due to the limited information in a single image and the poor adaptability of handcrafted priors.
Ranked #3 on
Low-Light Image Enhancement
on VV
Hint-dynamic Knowledge Distillation
Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher model to promote a smaller student model.
Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalization
Domain generalization (DG) enables generalizing a learning machine from multiple seen source domains to an unseen target one.
Uncertainty Inspired Underwater Image Enhancement
After that, we adopt a consensus process to predict a deterministic result based on a set of samples from the distribution.
Knowledge Condensation Distillation
Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher network to strengthen a smaller student.
Relation Matters: Foreground-aware Graph-based Relational Reasoning for Domain Adaptive Object Detection
However, both the global and local alignment approaches fail to capture the topological relations among different foreground objects as the explicit dependencies and interactions between and within domains are neglected.
A Closer Look at Personalization in Federated Image Classification
This paper shows that it is possible to achieve flexible personalization after the convergence of the global model by introducing representation learning.
AFSC: Adaptive Fourier Space Compression for Anomaly Detection
Data augmentation based methods construct pseudo-healthy images by "pasting" fake lesions on real healthy ones, and a network is trained to predict healthy images in a supervised manner.
Acoustic-Net: A Novel Neural Network for Sound Localization and Quantification
Acoustic source localization has been applied in different fields, such as aeronautics and ocean science, generally using multiple microphones array data to reconstruct the source location.
Harmonizing Pathological and Normal Pixels for Pseudo-healthy Synthesis
Comprehensive experiments on the T2 modality of BraTS demonstrate that the proposed method substantially outperforms the state-of-the-art methods.
Self-Verification in Image Denoising
Specifically, we treat the output of the network as a ``prior'' that we denoise again after ``re-noising''.
Domain Generalization on Medical Imaging Classification using Episodic Training with Task Augmentation
In this paper, we propose a novel DG scheme of episodic training with task augmentation on medical imaging classification.
GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
Deep Q Network (DQN) firstly kicked the door of deep reinforcement learning (DRL) via combining deep learning (DL) with reinforcement learning (RL), which has noticed that the distribution of the acquired data would change during the training process.
Ranked #1 on
Atari Games
on Atari 2600 Freeway
Hierarchical Deep Network with Uncertainty-aware Semi-supervised Learning for Vessel Segmentation
In this paper, to address the above issues, we propose a hierarchical deep network where an attention mechanism localizes the low-contrast capillary regions guided by the whole vessels, and enhance the spatial activation in those areas for the sub-type vessels.
Self-Regression Learning for Blind Hyperspectral Image Fusion Without Label
However, in real applications, the observation model involved are often complicated and unknown, which leads to the serious performance drop of many advanced HIF methods.
I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors
Motivated by this, we propose an Implicit Instance-Invariant Network (I3Net), which is tailored for adapting one-stage detectors and implicitly learns instance-invariant features via exploiting the natural characteristics of deep features in different layers.
Consistent Posterior Distributions under Vessel-Mixing: A Regularization for Cross-Domain Retinal Artery/Vein Classification
In this paper, we propose a novel vessel-mixing based consistency regularization framework, for cross-domain learning in retinal A/V classification.
Unsupervised Anomaly Segmentation using Image-Semantic Cycle Translation
In this paper, to alleviate this issue, we introduce the semantic space of healthy anatomy in the process of modeling healthy-data distribution.
Urban Surface Reconstruction in SAR Tomography by Graph-Cuts
This segmentation process can be included within the 3-D reconstruction framework in order to improve the recovery of urban surfaces.
Twice Mixing: A Rank Learning based Quality Assessment Approach for Underwater Image Enhancement
Our approach, termed Twice Mixing, is motivated by the observation that a mid-quality image can be generated by mixing a high-quality image with its low-quality version.
Hierarchical Meta Reinforcement Learning for Multi-Task Environments
To address the problem brought by the environment, we propose a Meta Soft Hierarchical reinforcement learning framework (MeSH), in which each low-level sub-policy focuses on a specific sub-task respectively and high-level policy automatically learns to utilize low-level sub-policies through meta-gradients.
Deep Reinforcement Learning
Hierarchical Reinforcement Learning
+3
Dual Bipartite Graph Learning: A General Approach for Domain Adaptive Object Detection
Domain Adaptive Object Detection (DAOD) relieves the reliance on large-scale annotated data by transferring the knowledge learned from a labeled source domain to a new unlabeled target domain.
Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding
Motivated by the spatial consistency and regularity in medical images, we developed an efficient global correlation module to capture the correlation between a support and query image and incorporate it into the deep network called global correlation network.
Adaptive noise imitation for image denoising
Coupling the noisy data output from ADANI with the corresponding ground-truth, a denoising CNN is then trained in a fully-supervised manner.
A Teacher-Student Framework for Semi-supervised Medical Image Segmentation From Mixed Supervision
We further proposed a localization branch realized via an aggregation of high-level features in a deep decoder to predict locations of organ and lesion, which enriches student segmentor with precise localization information.
Hard Class Rectification for Domain Adaptation
Second, we further consider that the predictions of target samples belonging to the hard class are vulnerable to perturbations.
Semi-supervised Domain Adaptation
Unsupervised Domain Adaptation
Harmonizing Transferability and Discriminability for Adapting Object Detectors
Recent advances in adaptive object detection have achieved compelling results in virtue of adversarial feature adaptation to mitigate the distributional shifts along the detection pipeline.
Noise2Blur: Online Noise Extraction and Denoising
Using the new image pair, the denoising network learns to generate clean and high-quality images from noisy observations.
Learning Rate Dropout
The uncertainty of the descent path helps the model avoid saddle points and bad local minima.
Multi-sequence Cardiac MR Segmentation with Adversarial Domain Adaptation Network
Automatic and accurate segmentation of the ventricles and myocardium from multi-sequence cardiac MRI (CMR) is crucial for the diagnosis and treatment management for patients suffering from myocardial infarction (MI).
Unsupervised Adversarial Graph Alignment with Graph Embedding
In this paper, we propose an Unsupervised Adversarial Graph Alignment (UAGA) framework to learn a cross-graph alignment between two embedding spaces of different graphs in a fully unsupervised fashion (\emph{i. e.,} no existing anchor links and no users' personal profile or attribute information is available).
Rain O'er Me: Synthesizing real rain to derain with data distillation
We present a supervised technique for learning to remove rain from images without using synthetic rain software.
A^2Net: Adjacent Aggregation Networks for Image Raindrop Removal
Existing methods for single images raindrop removal either have poor robustness or suffer from parameter burdens.
Progressive Feature Alignment for Unsupervised Domain Adaptation
Unsupervised domain adaptation (UDA) transfers knowledge from a label-rich source domain to a fully-unlabeled target domain.
Ranked #8 on
Domain Adaptation
on SVHN-to-MNIST
A Deep Tree-Structured Fusion Model for Single Image Deraining
We propose a simple yet effective deep tree-structured fusion model based on feature aggregation for the deraining problem.
An Adversarial Learning Approach to Medical Image Synthesis for Lesion Detection
Being able to provide a "normal" counterpart to a medical image can provide useful side information for medical imaging tasks like lesion segmentation or classification validated by our experiments.
Lightweight Pyramid Networks for Image Deraining
In this paper, we propose a lightweight pyramid of networks (LPNet) for single image deraining.
A Deeply-Recursive Convolutional Network for Crowd Counting
The estimation of crowd count in images has a wide range of applications such as video surveillance, traffic monitoring, public safety and urban planning.
Joint CS-MRI Reconstruction and Segmentation with a Unified Deep Network
The need for fast acquisition and automatic analysis of MRI data is growing in the age of big data.
A Deep Information Sharing Network for Multi-contrast Compressed Sensing MRI Reconstruction
In multi-contrast magnetic resonance imaging (MRI), compressed sensing theory can accelerate imaging by sampling fewer measurements within each contrast.
A Segmentation-aware Deep Fusion Network for Compressed Sensing MRI
In this paper, we proposed a segmentation-aware deep fusion network called SADFN for compressed sensing MRI.
A Divide-and-Conquer Approach to Compressed Sensing MRI
Compressed sensing (CS) theory assures us that we can accurately reconstruct magnetic resonance images using fewer k-space measurements than the Nyquist sampling rate requires.
A Deep Error Correction Network for Compressed Sensing MRI
Existing CS-MRI algorithms can serve as the template module for guiding the reconstruction.
PanNet: A Deep Network Architecture for Pan-Sharpening
We incorporate domain-specific knowledge to design our PanNet architecture by focusing on the two aims of the pan-sharpening problem: spectral and spatial preservation.
Removing Rain From Single Images via a Deep Detail Network
We propose a new deep network architecture for removing rain streaks from individual images based on the deep convolutional neural network (CNN).
A Weighted Variational Model for Simultaneous Reflectance and Illumination Estimation
We propose a weighted variational model to estimate both the reflectance and the illumination from an observed image.
Saliency Detection with Spaces of Background-based Distribution
In this letter, an effective image saliency detection method is proposed by constructing some novel spaces to model the background and redefine the distance of the salient patches away from the background.
Pan-Sharpening With a Hyper-Laplacian Penalty
Our objective incorporates the L1/2-norm in a way that can leverage recent computationally efficient methods, and L1 for which the alternating direction method of multipliers can be used.
HeteSim: A General Framework for Relevance Measure in Heterogeneous Networks
Similarity search is an important function in many applications, which usually focuses on measuring the similarity between objects with the same type.
Bayesian Nonparametric Dictionary Learning for Compressed Sensing MRI
The size of the dictionary and the patch-specific sparsity pattern are inferred from the data, in addition to other dictionary learning variables.
