Search Results for author:
Found 34 papers, 12 papers with code
Transitive Vision-Language Prompt Learning for Domain Generalization
The vision-language pre-training has enabled deep models to make a huge step forward in generalizing across unseen domains.
Large-Scale Multi-Domain Recommendation: an Automatic Domain Feature Extraction and Personalized Integration Framework
Besides, by personalized integration of domain features from other domains for each user and the innovation in the training mode, the DFEI framework can yield more accurate conversion identification.
Unified Multi-modal Diagnostic Framework with Reconstruction Pre-training and Heterogeneity-combat Tuning
Specifically, to enhance the representation abilities of vision and language encoders, we propose the Multi-level Reconstruction Pre-training (MR-Pretrain) strategy, including a feature-level and data-level reconstruction, which guides models to capture the semantic information from masked inputs of different modalities.
Unsupervised Learning for Joint Beamforming Design in RIS-aided ISAC Systems
It is critical to design efficient beamforming in reconfigurable intelligent surface (RIS)-aided integrated sensing and communication (ISAC) systems for enhancing spectrum utilization.
Endora: Video Generation Models as Endoscopy Simulators
In a nutshell, Endora marks a notable breakthrough in the deployment of generative AI for clinical endoscopy research, setting a substantial stage for further advances in medical content generation.
GaussianGrasper: 3D Language Gaussian Splatting for Open-vocabulary Robotic Grasping
In particular, we propose an Efficient Feature Distillation (EFD) module that employs contrastive learning to efficiently and accurately distill language embeddings derived from foundational models.
UN-SAM: Universal Prompt-Free Segmentation for Generalized Nuclei Images
Moreover, to unleash the generalization capability of SAM across a variety of nuclei images, we devise a Domain-adaptive Tuning Encoder (DT-Encoder) to seamlessly harmonize visual features with domain-common and domain-specific knowledge, and further devise a Domain Query-enhanced Decoder (DQ-Decoder) by leveraging learnable domain queries for segmentation decoding in different nuclei domains.
Exploiting Duality in Open Information Extraction with Predicate Prompt
Open information extraction (OpenIE) aims to extract the schema-free triplets in the form of (\emph{subject}, \emph{predicate}, \emph{object}) from a given sentence.
Energy Efficiency Optimization in Active Reconfigurable Intelligent Surface-Aided Integrated Sensing and Communication Systems
Energy efficiency (EE) is a challenging task in integrated sensing and communication (ISAC) systems, where high spectral efficiency and low energy consumption appear as conflicting requirements.
Surgical Temporal Action-aware Network with Sequence Regularization for Phase Recognition
Specifically, we propose an efficient multi-scale surgical temporal action (MS-STA) module, which integrates visual features with spatial and temporal knowledge of surgical actions at the cost of 2D networks.
PWISeg: Point-based Weakly-supervised Instance Segmentation for Surgical Instruments
To address this issue, we propose a novel yet effective weakly-supervised surgical instrument instance segmentation approach, named Point-based Weakly-supervised Instance Segmentation (PWISeg).
SurgPLAN: Surgical Phase Localization Network for Phase Recognition
To address these two challenges, we propose a Surgical Phase LocAlization Network, named SurgPLAN, to facilitate a more accurate and stable surgical phase recognition with the principle of temporal detection.
WS-YOLO: Weakly Supervised Yolo Network for Surgical Tool Localization in Endoscopic Videos
Being able to automatically detect and track surgical instruments in endoscopic video recordings would allow for many useful applications that could transform different aspects of surgery.
RT-MonoDepth: Real-time Monocular Depth Estimation on Embedded Systems
Depth sensing is a crucial function of unmanned aerial vehicles and autonomous vehicles.
PL-UNeXt: Per-stage Edge Detail and Line Feature Guided Segmentation for Power Line Detection
Power line detection is a critical inspection task for electricity companies and is also useful in avoiding drone obstacles.
Mutual Information Learned Regressor: an Information-theoretic Viewpoint of Training Regression Systems
We first argue that the MSE minimization approach is equivalent to a conditional entropy learning problem, and then propose a mutual information learning formulation for solving regression problems by using a reparameterization technique.
Improving Continual Relation Extraction through Prototypical Contrastive Learning
Continual relation extraction (CRE) aims to extract relations towards the continuous and iterative arrival of new data, of which the major challenge is the catastrophic forgetting of old tasks.
Neural Volumetric Mesh Generator
We first propose a diffusion-based generative model to tackle this problem by generating voxelized shapes with close-to-reality outlines and structures.
Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems
Deep learning systems have been reported to acheive state-of-the-art performances in many applications, and one of the keys for achieving this is the existence of well trained classifiers on benchmark datasets which can be used as backbone feature extractors in downstream tasks.
Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems
Deep learning systems have been reported to achieve state-of-the-art performances in many applications, and a key is the existence of well trained classifiers on benchmark datasets.
Robust Modeling of Unknown Dynamical Systems via Ensemble Averaged Learning
In the proposed ensemble averaging method, multiple models are independently trained and model predictions are averaged at each time step.
Exploring Gradient Flow Based Saliency for DNN Model Compression
Model pruning aims to reduce the deep neural network (DNN) model size or computational overhead.
A Deep Learning Inference Scheme Based on Pipelined Matrix Multiplication Acceleration Design and Non-uniform Quantization
Matrix multiplication is the bedrock in Deep Learning inference application.
Personalized Retrogress-Resilient Framework for Real-World Medical Federated Learning
To address this problem, we propose a personalized retrogress-resilient framework to produce a superior personalized model for each client.
Deep Neural Network Modeling of Unknown Partial Differential Equations in Nodal Space
Consequently, a trained DNN defines a predictive model for the underlying unknown PDE over structureless grids.
Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising
While considerable multi-task efforts have been made in this direction, a long-standing challenge is how to explicitly model the long-path sequential dependence among audience multi-step conversions for improving the end-to-end conversion.
Socially-Aware Conference Participant Recommendation with Personality Traits
As a result of the importance of academic collaboration at smart conferences, various researchers have utilized recommender systems to generate effective recommendations for participants.
Data-driven learning of non-autonomous systems
To circumvent the difficulty presented by the non-autonomous nature of the system, our method transforms the solution state into piecewise integration of the system over a discrete set of time instances.
Overcoming information reduced data and experimentally uncertain parameters in ptychography with regularized optimization
The overdetermination of the mathematical problem underlying ptychography is reduced by a host of experimentally more desirable settings.
Methods to Recover Unknown Processes in Partial Differential Equations Using Data
Various numerical examples are then presented to demonstrate the performance and properties of the numerical methods.
On generalized residue network for deep learning of unknown dynamical systems
When an existing coarse model is not available, we present numerical strategies for fast creation of coarse models, to be used in conjunction with the generalized ResNet.
Complementary Network with Adaptive Receptive Fields for Melanoma Segmentation
To tackle these issues, we propose a novel complementary network with adaptive receptive filed learning.
Parameterized Synthetic Image Data Set for Fisheye Lens
Based on different projection geometry, a fisheye image can be presented as a parameterized non-rectilinear image.
Deep Learning Framework for Multi-class Breast Cancer Histology Image Classification
In this work, we present a deep learning framework for multi-class breast cancer image classification as our submission to the International Conference on Image Analysis and Recognition (ICIAR) 2018 Grand Challenge on BreAst Cancer Histology images (BACH).
Breast Cancer Histology Image Classification
General Classification
+2
