Search Results for author:
Found 55 papers, 25 papers with code
PathBench: A comprehensive comparison benchmark for pathology foundation models towards precision oncology
Currently, our evaluation of 19 PFMs shows that Virchow2 and H-Optimus-1 are the most effective models overall.
Towards Robust Influence Functions with Flat Validation Minima
In this work, we establish a theoretical connection between influence estimation error, validation set risk, and its sharpness, underscoring the importance of flat validation minima for accurate influence estimation.
Discovering Pathology Rationale and Token Allocation for Efficient Multimodal Pathology Reasoning
Multimodal pathological image understanding has garnered widespread interest due to its potential to improve diagnostic accuracy and enable personalized treatment through integrated visual and textual data.
Angle Domain Guidance: Latent Diffusion Requires Rotation Rather Than Extrapolation
However, under high guidance weights, where text-image alignment is significantly enhanced, CFG also leads to pronounced color distortions in the generated images.
Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning
To this end, this paper proposes UnifiedReward-Think, the first unified multimodal CoT-based reward model, capable of multi-dimensional, step-by-step long-chain reasoning for both visual understanding and generation reward tasks.
Efficient Fine-Tuning of Quantized Models via Adaptive Rank and Bitwidth
QLoRA effectively combines low-bit quantization and LoRA to achieve memory-friendly fine-tuning for large language models (LLM).
Unified Reward Model for Multimodal Understanding and Generation
Recent advances in human preference alignment have significantly enhanced multimodal generation and understanding.
PsychBench: A comprehensive and professional benchmark for evaluating the performance of LLM-assisted psychiatric clinical practice
In response to this gap, by incorporating clinical demands in psychiatry and clinical data, we proposed a benchmarking system, PsychBench, to evaluate the practical performance of LLMs in psychiatric clinical settings.
Generalizable Cervical Cancer Screening via Large-scale Pretraining and Test-Time Adaptation
In retrospective cohorts, Smart-CCS achieved an overall area under the curve (AUC) value of 0. 965 and sensitivity of 0. 913 for cancer screening on 11 internal test datasets.
Population Normalization for Federated Learning
Second, estimating statistics from a mini-batch is often imprecise since the batch size has to be small in resource-limited clients.
HammerBench: Fine-Grained Function-Calling Evaluation in Real Mobile Device Scenarios
Evaluating the performance of LLMs in multi-turn human-agent interactions presents significant challenges, particularly due to the complexity and variability of user behavior.
Optimized Gradient Clipping for Noisy Label Learning
Previous research has shown that constraining the gradient of loss function with respect to model-predicted probabilities can enhance the model robustness against noisy labels.
LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment
Based on this, we train a reward model LiFT-Critic to learn reward function effectively, which serves as a proxy for human judgment, measuring the alignment between given videos and human expectations.
HMIL: Hierarchical Multi-Instance Learning for Fine-Grained Whole Slide Image Classification
Fine-grained classification of whole slide images (WSIs) is essential in precision oncology, enabling precise cancer diagnosis and personalized treatment strategies.
GameGen-X: Interactive Open-world Game Video Generation
To realize this vision, we first collected and built an Open-World Video Game Dataset from scratch.
MagicFace: Training-free Universal-Style Human Image Customized Synthesis
In the first stage, RSA enables the latent image to query features from all reference concepts simultaneously, extracting the overall semantic understanding to facilitate the initial semantic layout establishment.
MultiColor: Image Colorization by Learning from Multiple Color Spaces
Deep networks have shown impressive performance in the image restoration tasks, such as image colorization.
Towards A Generalizable Pathology Foundation Model via Unified Knowledge Distillation
Foundation models pretrained on large-scale datasets are revolutionizing the field of computational pathology (CPath).
A Multimodal Knowledge-enhanced Whole-slide Pathology Foundation Model
In this study, for the first time, we develop a pathology foundation model incorporating three levels of modalities: pathology slides, pathology reports, and gene expression data, which resulted in 26, 169 slide-level modality pairs from 10, 275 patients across 32 cancer types, amounting to over 116 million pathological patch images.
Minutes to Seconds: Speeded-up DDPM-based Image Inpainting with Coarse-to-Fine Sampling
Second, we introduce a skip-step sampling scheme of Denoising Diffusion Implicit Models (DDIM) for the denoising process.
Fine-Grained Scene Image Classification with Modality-Agnostic Adapter
In this paper, we present a new multi-modal feature fusion approach named MAA (Modality-Agnostic Adapter), trying to make the model learn the importance of different modalities in different cases adaptively, without giving a prior setting in the model architecture.
Unleashing the Denoising Capability of Diffusion Prior for Solving Inverse Problems
The proposed algorithm, termed ProjDiff, effectively harnesses the prior information and the denoising capability of a pre-trained diffusion model within the optimization framework.
DreamText: High Fidelity Scene Text Synthesis
Our key idea is to reconstruct the diffusion training process, introducing more refined guidance tailored to this task, to expose and rectify the model's attention at the character level and strengthen its learning of text regions.
ELiTe: Efficient Image-to-LiDAR Knowledge Transfer for Semantic Segmentation
Cross-modal knowledge transfer enhances point cloud representation learning in LiDAR semantic segmentation.
Robust Fine-tuning for Pre-trained 3D Point Cloud Models
We apply this robust fine-tuning method to mainstream 3D point cloud pre-trained models and evaluate the quality of model parameters and the degradation of downstream task performance.
Efficient scene text image super-resolution with semantic guidance
Scene text image super-resolution has significantly improved the accuracy of scene text recognition.
PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering
This prior information is encoded into the attention weights, which are then integrated into the self-attention layers of the generator to guide the synthesis process.
Out-of-Distribution Detection using Neural Activation Prior
Our neural activation prior is based on a key observation that, for a channel before the global pooling layer of a fully trained neural network, the probability of a few neurons being activated with a large response by an in-distribution (ID) sample is significantly higher than that by an OOD sample.
EPA: Neural Collapse Inspired Robust Out-of-Distribution Detector
Out-of-distribution (OOD) detection plays a crucial role in ensuring the security of neural networks.
PoseIRM: Enhance 3D Human Pose Estimation on Unseen Camera Settings via Invariant Risk Minimization
A natural solution is to artificially synthesize some samples i. e. 2D-3D pose pairs under massive new camera settings.
Point Cloud Part Editing: Segmentation, Generation, Assembly, and Selection
Based on this process, we introduce SGAS, a model for part editing that employs two strategies: feature disentanglement and constraint.
Shapley Values-enabled Progressive Pseudo Bag Augmentation for Whole Slide Image Classification
While most of the conventional MIL methods use attention scores to estimate instance importance scores (IIS) which contribute to the prediction of the slide labels, these often lead to skewed attention distributions and inaccuracies in identifying crucial instances.
UMAAF: Unveiling Aesthetics via Multifarious Attributes of Images
Then, to better utilize image attributes in aesthetic assessment, we propose the Unified Multi-attribute Aesthetic Assessment Framework (UMAAF) to model both absolute and relative attributes of images.
High-fidelity Person-centric Subject-to-Image Synthesis
Specifically, we first develop two specialized pre-trained diffusion models, i. e., Text-driven Diffusion Model (TDM) and Subject-augmented Diffusion Model (SDM), for scene and person generation, respectively.
DCQA: Document-Level Chart Question Answering towards Complex Reasoning and Common-Sense Understanding
Our DCQA dataset is expected to foster research on understanding visualizations in documents, especially for scenarios that require complex reasoning for charts in the visually-rich document.
Progressive Evidence Refinement for Open-domain Multimodal Retrieval Question Answering
Firstly, utilizing compressed evidence features as input to the model results in the loss of fine-grained information within the evidence.
ProtoEM: A Prototype-Enhanced Matching Framework for Event Relation Extraction
To comprehensively understand their intrinsic semantics, in this paper, we obtain prototype representations for each type of event relation and propose a Prototype-Enhanced Matching (ProtoEM) framework for the joint extraction of multiple kinds of event relations.
Linear Speedup of Incremental Aggregated Gradient Methods on Streaming Data
This paper considers a type of incremental aggregated gradient (IAG) method for large-scale distributed optimization.
The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation
In this paper, we summarize the winning solutions from the RoboDepth Challenge -- an academic competition designed to facilitate and advance robust OoD depth estimation.
WYTIWYR: A User Intent-Aware Framework with Multi-modal Inputs for Visualization Retrieval
Retrieving charts from a large corpus is a fundamental task that can benefit numerous applications such as visualization recommendations. The retrieved results are expected to conform to both explicit visual attributes (e. g., chart type, colormap) and implicit user intents (e. g., design style, context information) that vary upon application scenarios.
DDT: Dual-branch Deformable Transformer for Image Denoising
Transformer is beneficial for image denoising tasks since it can model long-range dependencies to overcome the limitations presented by inductive convolutional biases.
Label-Efficient Deep Learning in Medical Image Analysis: Challenges and Future Directions
Deep learning has significantly advanced medical imaging analysis (MIA), achieving state-of-the-art performance across diverse clinical tasks.
Aggregated Text Transformer for Scene Text Detection
We present the Aggregated Text TRansformer(ATTR), which is designed to represent texts in scene images with a multi-scale self-attention mechanism.
Progressive Scene Text Erasing with Self-Supervision
Scene text erasing seeks to erase text contents from scene images and current state-of-the-art text erasing models are trained on large-scale synthetic data.
SIT: A Bionic and Non-Linear Neuron for Spiking Neural Network
Spiking Neural Networks (SNNs) have piqued researchers' interest because of their capacity to process temporal information and low power consumption.
SRPCN: Structure Retrieval based Point Completion Network
Besides, the missing patterns are diverse in reality, but existing methods can only handle fixed ones, which means a poor generalization ability.
Cross-Domain Document Layout Analysis Using Document Style Guide
Our framework is an unsupervised document layout analysis framework.
Generate Point Clouds with Multiscale Details from Graph-Represented Structures
As details are missing in most representations of structures, the lack of controllability to more information is one of the major weaknesses in structure-based controllable point cloud generation.
Attention-based Transformation from Latent Features to Point Clouds
The points generated by AXform do not have the strong 2-manifold constraint, which improves the generation of non-smooth surfaces.
Safe Distillation Box
In other words, all users may employ a model in SDB for inference, but only authorized users get access to KD from the model.
Document Layout Analysis with Aesthetic-Guided Image Augmentation
To measure the proposed image layer modeling method, we propose a manually-labeled non-Manhattan layout fine-grained segmentation dataset named FPD.
Adaptive Charging Networks: A Framework for Smart Electric Vehicle Charging
We describe the architecture and algorithms of the Adaptive Charging Network (ACN), which was first deployed on the Caltech campus in early 2016 and is currently operating at over 100 other sites in the United States.
One-sample Guided Object Representation Disassembling
In this paper, we introduce the One-sample Guided Object Representation Disassembling (One-GORD) method, which only requires one annotated sample for each object category to learn disassembled object representation from unannotated images.
GASNet: Weakly-supervised Framework for COVID-19 Lesion Segmentation
Segmentation of infected areas in chest CT volumes is of great significance for further diagnosis and treatment of COVID-19 patients.
TripletGAN: Training Generative Model with Triplet Loss
As an effective way of metric learning, triplet loss has been widely used in many deep learning tasks, including face recognition and person-ReID, leading to many states of the arts.
