Search Results for author:
Found 67 papers, 8 papers with code
Skill-based Safe Reinforcement Learning with Risk Planning
In this paper, we propose a novel Safe Skill Planning (SSkP) approach to enhance effective safe RL by exploiting auxiliary offline demonstration data.
Safety Modulation: Enhancing Safety in Reinforcement Learning through Cost-Modulated Rewards
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.
Context-Aware Self-Adaptation for Domain Generalization
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.
Zero-Shot Action Generalization with Limited Observations
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.
Single Domain Generalization with Adversarial Memory
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.
Single Domain Generalization with Model-aware Parametric Batch-wise Mixup
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.
A Unified Framework for Heterogeneous Semi-supervised Learning
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.
Unbiased GNN Learning via Fairness-Aware Subgraph Diffusion
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.
Overcoming Class Imbalance: Unified GNN Learning with Structural and Semantic Connectivity Representations
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.
Skill-Enhanced Reinforcement Learning Acceleration from Demonstrations
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.
LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management
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).
vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving
This study introduces the vTensor, an innovative tensor structure for LLM inference based on GPU virtual memory management (VMM).
Reinforcement Learning-Guided Semi-Supervised Learning
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.
Cross-model Mutual Learning for Exemplar-based Medical Image Segmentation
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.
Prompt-Driven Feature Diffusion for Open-World Semi-Supervised Learning
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).
AKGNet: Attribute Knowledge-Guided Unsupervised Lung-Infected Area Segmentation
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.
Lightweight Unsupervised Federated Learning with Pretrained Vision Language Model
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.
Adaptive Weighted Co-Learning for Cross-Domain Few-Shot Learning
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.
Efficient Low-Rank GNN Defense Against Structural Attacks
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.
GDM: Dual Mixup for Graph Classification with Limited Supervision
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.
Evolving Dictionary Representation for Few-shot Class-incremental Learning
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.
Exemplar-FreeSOLO: Enhancing Unsupervised Instance Segmentation With Exemplars
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.
Annotation by Clicks: A Point-Supervised Contrastive Variance Method for Medical Semantic Segmentation
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.
Dual Moving Average Pseudo-Labeling for Source-Free Inductive Domain Adaptation
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
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).
Exemplar Learning for Medical Image Segmentation
Medical image annotation typically requires expert knowledge and hence incurs time-consuming and expensive data annotation costs.
Contrastive Continual Learning with Feature Propagation
To address this shortcoming, continual machine learners are elaborated to commendably learn a stream of tasks with domain and class shifts among different tasks.
Dual GNNs: Graph Neural Network Learning with Limited Supervision
In this paper, we propose a novel Dual GNN learning framework to address this challenge task.
Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentation
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.
Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation
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.
Domain Adaptation with Incomplete Target Domains
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.
Bi-Dimensional Feature Alignment for Cross-Domain Object Detection
Recently the problem of cross-domain object detection has started drawing attention in the computer vision community.
A Transductive Multi-Head Model for Cross-Domain Few-Shot Learning
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.
Ensemble Model with Batch Spectral Regularization and Data Blending for Cross-Domain Few-Shot Learning with Unlabeled Data
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.
Feature Transformation Ensemble Model with Batch Spectral Regularization for Cross-Domain Few-Shot Classification
In this paper, we propose a feature transformation ensemble model with batch spectral regularization for the Cross-domain few-shot learning (CD-FSL) challenge.
Multi-Level Generative Models for Partial Label Learning with Non-random Label Noise
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.
Unsupervised Domain Adaptation with Progressive Domain Augmentation
Domain adaptation aims to exploit a label-rich source domain for learning classifiers in a different label-scarce target domain.
Adaptive Object Detection with Dual Multi-Label Prediction
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.
Mutual Learning Network for Multi-Source Domain Adaptation
However, in practice the labeled data can come from multiple source domains with different distributions.
Time-aware Large Kernel Convolutions
Some of these models use all the available sequence tokens to generate an attention distribution which results in time complexity of $O(n^2)$.
Ranked #12 on
Machine Translation
on WMT2014 English-French
Adversarial Paritial Multi-label Learning
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.
Dual Adversarial Co-Learning for Multi-Domain Text Classification
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
In this paper, we propose a novel deep multi-level attention model to address inverse visual question answering.
Learning to Generate Questions with Adaptive Copying Neural Networks
Automatic question generation is an important problem in natural language processing.
Adversarial Partial Multi-Label Learning
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.
Object Detection in 20 Years: A Survey
Object detection, as of one the most fundamental and challenging problems in computer vision, has received great attention in recent years.
Multi-Label Zero-Shot Learning with Transfer-Aware Label Embedding Projection
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.
Progressive Ensemble Networks for Zero-Shot Recognition
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.
Visual relationship detection with deep structural ranking
In this paper, we propose a novel framework, called Deep Structural Ranking, for visual relationship detection.
Deep Triplet Ranking Networks for One-Shot Recognition
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.
Zero-Shot Classification With Discriminative Semantic Representation Learning
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.
Semi-Supervised Zero-Shot Classification With Label Representation Learning
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.
A Novel Two-Step Method for Cross Language Representation Learning
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.
Robust Transfer Principal Component Analysis with Rank Constraints
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.
Adaptive Active Learning for Image Classification
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 Instance Sampling via Matrix Partition
Recently, batch-mode active learning has attracted a lot of attention.
Supervised Exponential Family Principal Component Analysis via Convex Optimization
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.
Discriminative Batch Mode Active Learning
Most previous studies in active learning have focused on selecting one unlabeled instance at one time while retraining in each iteration.
