Search Results for author: Yuhong Guo

Found 67 papers, 8 papers with code

Skill-based Safe Reinforcement Learning with Risk Planning

no code implementations2 May 2025 Hanping Zhang, Yuhong Guo

In this paper, we propose a novel Safe Skill Planning (SSkP) approach to enhance effective safe RL by exploiting auxiliary offline demonstration data.

reinforcement-learning Reinforcement Learning +1

Safety Modulation: Enhancing Safety in Reinforcement Learning through Cost-Modulated Rewards

no code implementations3 Apr 2025 Hanping Zhang, Yuhong Guo

Safe Reinforcement Learning (Safe RL) aims to train an RL agent to maximize its performance in real-world environments while adhering to safety constraints, as exceeding safety violation limits can result in severe consequences.

Safe Reinforcement Learning

Context-Aware Self-Adaptation for Domain Generalization

no code implementations3 Apr 2025 Hao Yan, Yuhong Guo

Domain generalization aims at developing suitable learning algorithms in source training domains such that the model learned can generalize well on a different unseen testing domain.

Domain Generalization

Zero-Shot Action Generalization with Limited Observations

no code implementations11 Mar 2025 Abdullah Alchihabi, Hanping Zhang, Yuhong Guo

The action representation learning module extracts discriminative embeddings of actions from limited observations, while the policy learning module leverages the learned action representations, along with augmented synthetic action representations, to learn a policy capable of handling tasks with unseen actions.

Decision Making Reinforcement Learning (RL) +2

Single Domain Generalization with Adversarial Memory

no code implementations8 Mar 2025 Hao Yan, Marzi Heidari, Yuhong Guo

To maintain a diverse and representative feature memory bank, we introduce an adversarial feature generation method that creates features extending beyond the training domain distribution.

Diversity Domain Generalization

Single Domain Generalization with Model-aware Parametric Batch-wise Mixup

no code implementations22 Feb 2025 Marzi Heidari, Yuhong Guo

Single Domain Generalization (SDG) remains a formidable challenge in the field of machine learning, particularly when models are deployed in environments that differ significantly from their training domains.

Data Augmentation Domain Generalization

A Unified Framework for Heterogeneous Semi-supervised Learning

no code implementations CVPR 2025 Marzi Heidari, Abdullah Alchihabi, Hao Yan, Yuhong Guo

In this work, we introduce a novel problem setup termed as Heterogeneous Semi-Supervised Learning (HSSL), which presents unique challenges by bridging the semi-supervised learning (SSL) task and the unsupervised domain adaptation (UDA) task, and expanding standard semi-supervised learning to cope with heterogeneous training data.

Transfer Learning Unsupervised Domain Adaptation

Unbiased GNN Learning via Fairness-Aware Subgraph Diffusion

no code implementations31 Dec 2024 Abdullah Alchihabi, Yuhong Guo

To effectively diffuse unfairness in the input data, we introduce additional adversary bias perturbations to the subgraphs during the forward diffusion process, and train score-based models to predict these applied perturbations, enabling them to learn the underlying dynamics of the biases present in the data.

Fairness

Overcoming Class Imbalance: Unified GNN Learning with Structural and Semantic Connectivity Representations

no code implementations30 Dec 2024 Abdullah Alchihabi, Hao Yan, Yuhong Guo

Class imbalance is pervasive in real-world graph datasets, where the majority of annotated nodes belong to a small set of classes (majority classes), leaving many other classes (minority classes) with only a handful of labeled nodes.

Graph Learning Graph Neural Network +2

Skill-Enhanced Reinforcement Learning Acceleration from Demonstrations

no code implementations9 Dec 2024 Hanping Zhang, Yuhong Guo

SeRLA introduces a skill-level adversarial Positive-Unlabeled (PU) learning model to extract useful skill prior knowledge by enabling learning from both limited expert data and general low-cost demonstration data in the offline prior learning stage.

reinforcement-learning Reinforcement Learning +1

LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management

1 code implementation1 Oct 2024 Yi Xiong, Hao Wu, Changxu Shao, Ziqing Wang, Rui Zhang, Yuhong Guo, Junping Zhao, Ke Zhang, Zhenxuan Pan

The expanding context windows in large language models (LLMs) have greatly enhanced their capabilities in various applications, but they also introduce significant challenges in maintaining low latency, particularly in Time to First Token (TTFT).

Language Modeling Language Modelling +3

vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving

1 code implementation22 Jul 2024 Jiale Xu, Rui Zhang, Cong Guo, Weiming Hu, Zihan Liu, Feiyang Wu, Yu Feng, Shixuan Sun, Changxu Shao, Yuhong Guo, Junping Zhao, Ke Zhang, Minyi Guo, Jingwen Leng

This study introduces the vTensor, an innovative tensor structure for LLM inference based on GPU virtual memory management (VMM).

Management

Reinforcement Learning-Guided Semi-Supervised Learning

no code implementations2 May 2024 Marzi Heidari, Hanping Zhang, Yuhong Guo

In recent years, semi-supervised learning (SSL) has gained significant attention due to its ability to leverage both labeled and unlabeled data to improve model performance, especially when labeled data is scarce.

reinforcement-learning Reinforcement Learning +1

Cross-model Mutual Learning for Exemplar-based Medical Image Segmentation

no code implementations18 Apr 2024 Qing En, Yuhong Guo

In this paper, we introduce a novel Cross-model Mutual learning framework for Exemplar-based Medical image Segmentation (CMEMS), which leverages two models to mutually excavate implicit information from unlabeled data at multiple granularities.

Image Segmentation Medical Image Segmentation +2

Prompt-Driven Feature Diffusion for Open-World Semi-Supervised Learning

no code implementations17 Apr 2024 Marzi Heidari, Hanping Zhang, Yuhong Guo

In this paper, we present a novel approach termed Prompt-Driven Feature Diffusion (PDFD) within a semi-supervised learning framework for Open World Semi-Supervised Learning (OW-SSL).

Open-World Semi-Supervised Learning Representation Learning

AKGNet: Attribute Knowledge-Guided Unsupervised Lung-Infected Area Segmentation

no code implementations17 Apr 2024 Qing En, Yuhong Guo

It can learn statistical information and capture spatial correlations between image and text attributes in the embedding space, iteratively refining the mask to enhance segmentation.

Attribute Pseudo Label +1

Lightweight Unsupervised Federated Learning with Pretrained Vision Language Model

no code implementations17 Apr 2024 Hao Yan, Yuhong Guo

To address these two inherent challenges in supervised federated learning, we propose a novel lightweight unsupervised federated learning approach that leverages unlabeled data on each client to perform lightweight model training and communication by harnessing pretrained vision-language models, such as CLIP.

Federated Learning Language Modeling +1

Adaptive Weighted Co-Learning for Cross-Domain Few-Shot Learning

no code implementations6 Dec 2023 Abdullah Alchihabi, Marzi Heidari, Yuhong Guo

Due to the availability of only a few labeled instances for the novel target prediction task and the significant domain shift between the well annotated source domain and the target domain, cross-domain few-shot learning (CDFSL) induces a very challenging adaptation problem.

cross-domain few-shot learning

Efficient Low-Rank GNN Defense Against Structural Attacks

no code implementations18 Sep 2023 Abdullah Alchihabi, Qing En, Yuhong Guo

As a result, instead of using the dense adjacency matrix directly, ELR-GNN can learn a low-rank and sparse estimate of it in a simple, efficient and easy to optimize manner.

Graph Neural Network

GDM: Dual Mixup for Graph Classification with Limited Supervision

no code implementations18 Sep 2023 Abdullah Alchihabi, Yuhong Guo

In this work, we propose a novel mixup-based graph augmentation method, Graph Dual Mixup (GDM), that leverages both functional and structural information of the graph instances to generate new labeled graph samples.

Diversity Graph Classification +1

Evolving Dictionary Representation for Few-shot Class-incremental Learning

no code implementations3 May 2023 Xuejun Han, Yuhong Guo

In view of this, in this paper we tackle a challenging and practical continual learning scenario named few-shot class-incremental learning (FSCIL), in which labeled data are given for classes in a base session but very limited labeled instances are available for new incremental classes.

class-incremental learning Dictionary Learning +3

Exemplar-FreeSOLO: Enhancing Unsupervised Instance Segmentation With Exemplars

no code implementations CVPR 2023 Taoseef Ishtiak, Qing En, Yuhong Guo

Moreover, a new exemplar embedding contrastive module is designed to enhance the discriminative capability of the segmentation model by exploiting the contrastive exemplar-based guidance knowledge in the embedding space.

Instance Segmentation Segmentation +2

Annotation by Clicks: A Point-Supervised Contrastive Variance Method for Medical Semantic Segmentation

no code implementations17 Dec 2022 Qing En, Yuhong Guo

The proposed method trains the base segmentation network by using a novel contrastive variance (CV) loss to exploit the unlabeled pixels and a partial cross-entropy loss on the labeled pixels.

Image Segmentation Medical Image Segmentation +2

Dual Moving Average Pseudo-Labeling for Source-Free Inductive Domain Adaptation

no code implementations15 Dec 2022 Hao Yan, Yuhong Guo

We first split the unlabeled training set in the target domain into a pseudo-labeled confident subset and an unlabeled less-confident subset according to the prediction confidence scores from the pre-trained source model.

Source-Free Domain Adaptation Unsupervised Domain Adaptation

Safe Reinforcement Learning with Contrastive Risk Prediction

no code implementations10 Sep 2022 Hanping Zhang, Yuhong Guo

As safety violations can lead to severe consequences in real-world robotic applications, the increasing deployment of Reinforcement Learning (RL) in robotic domains has propelled the study of safe exploration for reinforcement learning (safe RL).

Prediction reinforcement-learning +4

Exemplar Learning for Medical Image Segmentation

no code implementations3 Apr 2022 Qing En, Yuhong Guo

Medical image annotation typically requires expert knowledge and hence incurs time-consuming and expensive data annotation costs.

Image Segmentation Medical Image Segmentation +6

Contrastive Continual Learning with Feature Propagation

no code implementations3 Dec 2021 Xuejun Han, Yuhong Guo

To address this shortcoming, continual machine learners are elaborated to commendably learn a stream of tasks with domain and class shifts among different tasks.

Continual Learning Representation Learning

Dual GNNs: Graph Neural Network Learning with Limited Supervision

no code implementations29 Jun 2021 Abdullah Alchihabi, Yuhong Guo

In this paper, we propose a novel Dual GNN learning framework to address this challenge task.

Graph Neural Network Node Classification

Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentation

no code implementations29 Jun 2021 Hanping Zhang, Yuhong Guo

In this work, we propose a novel policy-aware adversarial data augmentation method to augment the standard policy learning method with automatically generated trajectory data.

Data Augmentation Diversity +3

Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation

no code implementations7 Dec 2020 Bingyu Liu, Yuhong Guo, Jieping Ye, Weihong Deng

Inspired by the effectiveness of pseudo-labels in domain adaptation, we propose a reinforcement learning based selective pseudo-labeling method for semi-supervised domain adaptation.

Q-Learning reinforcement-learning +3

Domain Adaptation with Incomplete Target Domains

no code implementations3 Dec 2020 Zhenpeng Li, Jianan Jiang, Yuhong Guo, Tiantian Tang, Chengxiang Zhuo, Jieping Ye

In the proposed model, we design a data imputation module to fill the missing feature values based on the partial observations in the target domain, while aligning the two domains via deep adversarial adaption.

Domain Adaptation Imputation

Bi-Dimensional Feature Alignment for Cross-Domain Object Detection

no code implementations14 Nov 2020 Zhen Zhao, Yuhong Guo, Jieping Ye

Recently the problem of cross-domain object detection has started drawing attention in the computer vision community.

Object Object Detection +1

A Transductive Multi-Head Model for Cross-Domain Few-Shot Learning

1 code implementation8 Jun 2020 Jianan Jiang, Zhenpeng Li, Yuhong Guo, Jieping Ye

The TMHFS method extends the Meta-Confidence Transduction (MCT) and Dense Feature-Matching Networks (DFMN) method [2] by introducing a new prediction head, i. e, an instance-wise global classification network based on semantic information, after the common feature embedding network.

cross-domain few-shot learning Data Augmentation

Ensemble Model with Batch Spectral Regularization and Data Blending for Cross-Domain Few-Shot Learning with Unlabeled Data

1 code implementation8 Jun 2020 Zhen Zhao, Bingyu Liu, Yuhong Guo, Jieping Ye

In this paper, we present our proposed ensemble model with batch spectral regularization and data blending mechanisms for the Track 2 problem of the cross-domain few-shot learning (CD-FSL) challenge.

cross-domain few-shot learning

Feature Transformation Ensemble Model with Batch Spectral Regularization for Cross-Domain Few-Shot Classification

no code implementations18 May 2020 Bingyu Liu, Zhen Zhao, Zhenpeng Li, Jianan Jiang, Yuhong Guo, Jieping Ye

In this paper, we propose a feature transformation ensemble model with batch spectral regularization for the Cross-domain few-shot learning (CD-FSL) challenge.

cross-domain few-shot learning Data Augmentation +2

Multi-Level Generative Models for Partial Label Learning with Non-random Label Noise

no code implementations11 May 2020 Yan Yan, Yuhong Guo

Partial label (PL) learning tackles the problem where each training instance is associated with a set of candidate labels that include both the true label and irrelevant noise labels.

Denoising Partial Label Learning

Unsupervised Domain Adaptation with Progressive Domain Augmentation

no code implementations3 Apr 2020 Kevin Hua, Yuhong Guo

Domain adaptation aims to exploit a label-rich source domain for learning classifiers in a different label-scarce target domain.

Unsupervised Domain Adaptation

Adaptive Object Detection with Dual Multi-Label Prediction

no code implementations ECCV 2020 Zhen Zhao, Yuhong Guo, Haifeng Shen, Jieping Ye

In this paper, we propose a novel end-to-end unsupervised deep domain adaptation model for adaptive object detection by exploiting multi-label object recognition as a dual auxiliary task.

Image-to-Image Translation Object +5

Mutual Learning Network for Multi-Source Domain Adaptation

no code implementations29 Mar 2020 Zhenpeng Li, Zhen Zhao, Yuhong Guo, Haifeng Shen, Jieping Ye

However, in practice the labeled data can come from multiple source domains with different distributions.

Unsupervised Domain Adaptation

Time-aware Large Kernel Convolutions

1 code implementation ICML 2020 Vasileios Lioutas, Yuhong Guo

Some of these models use all the available sequence tokens to generate an attention distribution which results in time complexity of $O(n^2)$.

Document Summarization Language Modeling +3

Adversarial Paritial Multi-label Learning

no code implementations ICLR 2020 Yan Yan, Yuhong Guo

Partial multi-label learning (PML), which tackles the problem of learning multi-label prediction models from instances with overcomplete noisy annotations, has recently started gaining attention from the research community.

Decoder Generative Adversarial Network +1

Dual Adversarial Co-Learning for Multi-Domain Text Classification

no code implementations18 Sep 2019 Yuan Wu, Yuhong Guo

In this paper we propose a novel dual adversarial co-learning approach for multi-domain text classification (MDTC).

General Classification Multi-Domain Sentiment Classification +4

Inverse Visual Question Answering with Multi-Level Attentions

no code implementations17 Sep 2019 Yaser Alwattar, Yuhong Guo

In this paper, we propose a novel deep multi-level attention model to address inverse visual question answering.

Question Answering Visual Question Answering

Adversarial Partial Multi-Label Learning

no code implementations15 Sep 2019 Yan Yan, Yuhong Guo

Partial multi-label learning (PML), which tackles the problem of learning multi-label prediction models from instances with overcomplete noisy annotations, has recently started gaining attention from the research community.

Decoder Generative Adversarial Network +1

Object Detection in 20 Years: A Survey

1 code implementation13 May 2019 Zhengxia Zou, Keyan Chen, Zhenwei Shi, Yuhong Guo, Jieping Ye

Object detection, as of one the most fundamental and challenging problems in computer vision, has received great attention in recent years.

Face Detection Object +4

Multi-Label Zero-Shot Learning with Transfer-Aware Label Embedding Projection

no code implementations7 Aug 2018 Meng Ye, Yuhong Guo

The approach projects the label embedding vectors into a low-dimensional space to induce better inter-label relationships and explicitly facilitate information transfer from seen labels to unseen labels, while simultaneously learning a max-margin multi-label classifier with the projected label embeddings.

image-classification Multi-Label Image Classification +2

Progressive Ensemble Networks for Zero-Shot Recognition

no code implementations CVPR 2019 Meng Ye, Yuhong Guo

The ensemble network is built by learning multiple image classification functions with a shared feature extraction network but different label embedding representations, which enhance the diversity of the classifiers and facilitate information transfer to unlabeled classes.

Diversity Generalized Zero-Shot Learning +2

Deep Triplet Ranking Networks for One-Shot Recognition

1 code implementation19 Apr 2018 Meng Ye, Yuhong Guo

Despite the breakthroughs achieved by deep learning models in conventional supervised learning scenarios, their dependence on sufficient labeled training data in each class prevents effective applications of these deep models in situations where labeled training instances for a subset of novel classes are very sparse -- in the extreme case only one instance is available for each class.

One-Shot Learning Triplet

Zero-Shot Classification With Discriminative Semantic Representation Learning

no code implementations CVPR 2017 Meng Ye, Yuhong Guo

The proposed approach aims to identify a set of common high-level semantic components across the two domains via non-negative sparse matrix factorization, while enforcing the representation vectors of the images in this common component-based space to be discriminatively aligned with the attribute-based label representation vectors.

Attribute Classification +5

Semi-Supervised Zero-Shot Classification With Label Representation Learning

no code implementations ICCV 2015 Xin Li, Yuhong Guo, Dale Schuurmans

Most existing zero-shot learning methods require a user to first provide a set of semantic visual attributes for each class as side information before applying a two-step prediction procedure that introduces an intermediate attribute prediction problem.

Attribute General Classification +5

A Novel Two-Step Method for Cross Language Representation Learning

no code implementations NeurIPS 2013 Min Xiao, Yuhong Guo

In this paper, we propose a two-step representation learning method to bridge the feature spaces of different languages by exploiting a set of parallel bilingual documents.

Matrix Completion Representation Learning +1

Robust Transfer Principal Component Analysis with Rank Constraints

no code implementations NeurIPS 2013 Yuhong Guo

Our method is based on the assumption that useful information for the recovery of a corrupted data matrix can be gained from an uncorrupted related data matrix.

Dimensionality Reduction Image Denoising

Adaptive Active Learning for Image Classification

no code implementations CVPR 2013 Xin Li, Yuhong Guo

Recently active learning has attracted a lot of attention in computer vision field, as it is time and cost consuming to prepare a good set of labeled images for vision data analysis.

Active Learning Classification +5

Supervised Exponential Family Principal Component Analysis via Convex Optimization

no code implementations NeurIPS 2008 Yuhong Guo

Recently, supervised dimensionality reduction has been gaining attention, owing to the realization that data labels are often available and strongly suggest important underlying structures in the data.

global-optimization Supervised dimensionality reduction

Discriminative Batch Mode Active Learning

no code implementations NeurIPS 2007 Yuhong Guo, Dale Schuurmans

Most previous studies in active learning have focused on selecting one unlabeled instance at one time while retraining in each iteration.

Active Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.