Search Results for author:
Found 65 papers, 15 papers with code
A Deep Q-Network Based on Radial Basis Functions for Multi-Echelon Inventory Management
This paper addresses a multi-echelon inventory management problem with a complex network topology where deriving optimal ordering decisions is difficult.
MST: Adaptive Multi-Scale Tokens Guided Interactive Segmentation
To address the target scale variation issue in interactive segmentation, a novel multi-scale token adaptation algorithm is proposed.
Ranked #1 on
Interactive Segmentation
on DAVIS-585
Identity-Obscured Neural Radiance Fields: Privacy-Preserving 3D Facial Reconstruction
Neural radiance fields (NeRF) typically require a complete set of images taken from multiple camera perspectives to accurately reconstruct geometric details.
Ask Language Model to Clean Your Noisy Translation Data
Lastly, experiments on C-MTNT showcased its effectiveness in evaluating the robustness of NMT models, highlighting the potential of advanced language models for data cleaning and emphasizing C-MTNT as a valuable resource.
HoloFed: Environment-Adaptive Positioning via Multi-band Reconfigurable Holographic Surfaces and Federated Learning
Our simulation results confirm that HoloFed achieves a 57% lower positioning error variance compared to a beam-scanning baseline and can effectively adapt to diverse environments.
OCHID-Fi: Occlusion-Robust Hand Pose Estimation in 3D via RF-Vision
To overcome the challenge in labeling RF imaging given its human incomprehensible nature, OCHID-Fi employs a cross-modality and cross-domain training process.
FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning
Personalized Federated Learning (PFL) represents a promising solution for decentralized learning in heterogeneous data environments.
EFLNet: Enhancing Feature Learning for Infrared Small Target Detection
To address this problem, we propose a new adaptive threshold focal loss (ATFL) function that decouples the target and the background, and utilizes the adaptive mechanism to adjust the loss weight to force the model to allocate more attention to target features.
Multi-band Reconfigurable Holographic Surface Based ISAC Systems: Design and Optimization
Metamaterial-based reconfigurable holographic surfaces (RHSs) have been proposed as novel cost-efficient antenna arrays, which are promising for improving the positioning and communication performance of integrated sensing and communications (ISAC) systems.
On Hierarchical Multi-Resolution Graph Generative Models
In real world domains, most graphs naturally exhibit a hierarchical structure.
AutoFed: Heterogeneity-Aware Federated Multimodal Learning for Robust Autonomous Driving
Object detection with on-board sensors (e. g., lidar, radar, and camera) play a crucial role in autonomous driving (AD), and these sensors complement each other in modalities.
Human not in the loop: objective sample difficulty measures for Curriculum Learning
Curriculum learning is a learning method that trains models in a meaningful order from easier to harder samples.
A Simple Decentralized Cross-Entropy Method
To tackle this issue, we propose Decentralized CEM (DecentCEM), a simple but effective improvement over classical CEM, by using an ensemble of CEM instances running independently from one another, and each performing a local improvement of its own sampling distribution.
Dynamic Decision Frequency with Continuous Options
In classic reinforcement learning algorithms, agents make decisions at discrete and fixed time intervals.
PGFed: Personalize Each Client's Global Objective for Federated Learning
Based on our observation, in this work, we propose Personalized Global Federated Learning (PGFed), a novel personalized FL framework that enables each client to personalize its own global objective by explicitly and adaptively aggregating the empirical risks of itself and other clients.
Label Alignment Regularization for Distribution Shift
Recent work has highlighted the label alignment property (LAP) in supervised learning, where the vector of all labels in the dataset is mostly in the span of the top few singular vectors of the data matrix.
NeurIPS 2022 Competition: Driving SMARTS
The proposed competition supports methodologically diverse solutions, such as reinforcement learning (RL) and offline learning methods, trained on a combination of naturalistic AD data and open-source simulation platform SMARTS.
Build generally reusable agent-environment interaction models
This paper tackles the problem of how to pre-train a model and make it generally reusable backbones for downstream task learning.
Auxiliary task discovery through generate-and-test
In this paper, we explore an approach to auxiliary task discovery in reinforcement learning based on ideas from representation learning.
Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation
The experience replay buffer, a standard component in deep reinforcement learning, is often used to reduce forgetting and improve sample efficiency by storing experiences in a large buffer and using them for training later.
Reinforcement Teaching
To effectively learn such a teaching policy, we introduce a parametric-behavior embedder that learns a representation of the student's learnable parameters from its input/output behavior.
What makes useful auxiliary tasks in reinforcement learning: investigating the effect of the target policy
Our focus on the role of the target policy of the auxiliary tasks is motivated by the fact that the target policy determines the behavior about which the agent wants to make a prediction and the state-action distribution that the agent is trained on, which further affects the main task learning.
LatentFormer: Multi-Agent Transformer-Based Interaction Modeling and Trajectory Prediction
Multi-agent trajectory prediction is a fundamental problem in autonomous driving.
Drawing Inductor Layout with a Reinforcement Learning Agent: Method and Application for VCO Inductors
In light of the need to tweak the target specifications throughout the circuit design cycle, we also develop a variant in which the agent can learn to quickly adapt to draw new inductors for moderately different target specifications.
Adv-4-Adv: Thwarting Changing Adversarial Perturbations via Adversarial Domain Adaptation
Whereas adversarial training can be useful against specific adversarial perturbations, they have also proven ineffective in generalizing towards attacks deviating from those used for training.
MoRe-Fi: Motion-robust and Fine-grained Respiration Monitoring via Deep-Learning UWB Radar
Crucial for healthcare and biomedical applications, respiration monitoring often employs wearable sensors in practice, causing inconvenience due to their direct contact with human bodies.
RF-Net: a Unified Meta-learning Framework for RF-enabled One-shot Human Activity Recognition
Radio-Frequency (RF) based device-free Human Activity Recognition (HAR) rises as a promising solution for many applications.
Enhancing RF Sensing with Deep Learning: A Layered Approach
To better understand this potential, this article takes a layered approach to summarize RF sensing enabled by deep learning.
V2iFi: in-Vehicle Vital Sign Monitoring via Compact RF Sensing
Given the significant amount of time people spend in vehicles, health issues under driving condition have become a major concern.
SiWa: See into Walls via Deep UWB Radar
To this end, we equip SiWa with a deep learning pipeline to parse the rich sensory data.
Deep Curriculum Learning in Task Space for Multi-Class Based Mammography Diagnosis
In this work, we propose an end-to-end Curriculum Learning (CL) strategy in task space for classifying the three categories of Full-Field Digital Mammography (FFDM), namely Malignant, Negative, and False recall.
Knowledge-Guided Multiview Deep Curriculum Learning for Elbow Fracture Classification
We evaluate our method through extensive experiments on a classification task of elbow fracture with a dataset of 1, 964 images.
Medical Knowledge-Guided Deep Curriculum Learning for Elbow Fracture Diagnosis from X-Ray Images
We design an experiment with 1865 elbow X-ray images for a fracture/normal binary classification task and compare our proposed method to a baseline method and a previous method using multiple metrics.
Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learning
We also introduce a method to flexibly control the focus of training APPLE between global and local objectives.
FedSLD: Federated Learning with Shared Label Distribution for Medical Image Classification
Machine learning in medical research, by nature, needs careful attention on obeying the regulations of data privacy, making it difficult to train a machine learning model over gathered data from different medical centers.
Multi-lane Cruising Using Hierarchical Planning and Reinforcement Learning
Competent multi-lane cruising requires using lane changes and within-lane maneuvers to achieve good speed and maintain safety.
Adapt to Adaptation: Learning to Personalize for Cross-Silo Federated Learning
We also introduce a method to flexibly control the focus of training APPLE between global and local objectives.
Decentralized Cross-Entropy Method for Model-Based Reinforcement Learning
Further, we extend the decentralized approach to sequential decision-making problems where we show in 13 continuous control benchmark environments that it matches or outperforms the state-of-the-art CEM algorithms in most cases, under the same budget of the total number of samples for planning.
Variational Component Decoder for Source Extraction from Nonlinear Mixture
In many practical scenarios of signal extraction from a nonlinear mixture, only one (signal) source is intended to be extracted.
Disentangling Generalization in Reinforcement Learning
The resulting environment, while simple, necessitates function approximation for state abstraction and provides ground-truth labels for optimal policies and value functions.
Cooperative Multi-Agent Transfer Learning with Level-Adaptive Credit Assignment
In addition, we use a novel agent network named Population Invariant agent with Transformer (PIT) to realize the coordination transfer in more varieties of scenarios.
Probing the Effect of Selection Bias on Generalization: A Thought Experiment
The point of the thought experiment is not to demonstrate problems with all learned systems.
PURE: Passive mUlti-peRson idEntification via Deep Footstep Separation and Recognition
Recently, \textit{passive behavioral biometrics} (e. g., gesture or footstep) have become promising complements to conventional user identification methods (e. g., face or fingerprint) under special situations, yet existing sensing technologies require lengthy measurement traces and cannot identify multiple users at the same time.
Self-Supervised Simultaneous Multi-Step Prediction of Road Dynamics and Cost Map
While supervised learning is widely used for perception modules in conventional autonomous driving solutions, scalability is hindered by the huge amount of data labeling needed.
Open-set Intersection Intention Prediction for Autonomous Driving
We capture map-centric features that correspond to intersection structures under a spatial-temporal graph representation, and use two MAAMs (mutually auxiliary attention module) that cover respectively lane-level and exitlevel intentions to predict a target that best matches intersection elements in map-centric feature space.
Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems
Multiagent reinforcement learning (MARL) has achieved a remarkable amount of success in solving various types of video games.
CoachNet: An Adversarial Sampling Approach for Reinforcement Learning
Despite the recent successes of reinforcement learning in games and robotics, it is yet to become broadly practical.
LISPR: An Options Framework for Policy Reuse with Reinforcement Learning
Our approach facilitates the learning of new policies by (1) maximizing the target MDP reward with the help of the black-box option, and (2) returning the agent to states in the learned initiation set of the black-box option where it is already optimal.
Prediction by Anticipation: An Action-Conditional Prediction Method based on Interaction Learning
In autonomous driving (AD), accurately predicting changes in the environment can effectively improve safety and comfort.
PePScenes: A Novel Dataset and Baseline for Pedestrian Action Prediction in 3D
To this end, we propose a new pedestrian action prediction dataset created by adding per-frame 2D/3D bounding box and behavioral annotations to the popular autonomous driving dataset, nuScenes.
Bifold and Semantic Reasoning for Pedestrian Behavior Prediction
Our method benefits from 1) a bifold encoding approach where different data modalities are processed independently allowing them to develop their own representations, and jointly to produce a representation for all modalities using shared parameters; 2) a novel interaction modeling technique that relies on categorical semantic parsing of the scenes to capture interactions between target pedestrians and their surroundings; and 3) a bifold prediction mechanism that uses both independent and shared decoding of multimodal representations.
Graph-SIM: A Graph-based Spatiotemporal Interaction Modelling for Pedestrian Action Prediction
2) We introduce a new dataset that provides 3D bounding box and pedestrian behavioural annotations for the existing nuScenes dataset.
Multi-Modal Hybrid Architecture for Pedestrian Action Prediction
Pedestrian behavior prediction is one of the major challenges for intelligent driving systems in urban environments.
Offline Learning of Counterfactual Predictions for Real-World Robotic Reinforcement Learning
We consider real-world reinforcement learning (RL) of robotic manipulation tasks that involve both visuomotor skills and contact-rich skills.
No Perfect Outdoors: Towards A Deep Profiling of GNSS-based Location Contexts
On one hand, we offer a more fine-grained semantic classification than binary indoor-outdoor detection.
Networking and Internet Architecture
Affordance as general value function: A computational model
General value functions (GVFs) in the reinforcement learning (RL) literature are long-term predictive summaries of the outcomes of agents following specific policies in the environment.
SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving
We open-source the SMARTS platform and the associated benchmark tasks and evaluation metrics to encourage and empower research on multi-agent learning for autonomous driving.
Review on Ranking and Selection: A New Perspective
In this paper, we briefly review the development of ranking-and-selection (R&S) in the past 70 years, especially the theoretical achievements and practical applications in the last 20 years.
Optimization and Control Methodology
Understanding and Mitigating the Limitations of Prioritized Experience Replay
Prioritized Experience Replay (ER) has been empirically shown to improve sample efficiency across many domains and attracted great attention; however, there is little theoretical understanding of why such prioritized sampling helps and its limitations.
Enhancing Intrinsic Adversarial Robustness via Feature Pyramid Decoder
Whereas adversarial training is employed as the main defence strategy against specific adversarial samples, it has limited generalization capability and incurs excessive time complexity.
Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning
Social psychology and real experiences show that cognitive consistency plays an important role to keep human society in order: if people have a more consistent cognition about their environments, they are more likely to achieve better cooperation.
Reward Advancement: Transforming Policy under Maximum Causal Entropy Principle
In this paper, we define and investigate a general reward trans-formation problem (namely, reward advancement): Recovering the range of additional reward functions that transform the agent's policy from original policy to a predefined target policy under MCE principle.
Adaptive Hierarchical Down-Sampling for Point Cloud Classification
While several convolution-like operators have recently been proposed for extracting features out of point clouds, down-sampling an unordered point cloud in a deep neural network has not been rigorously studied.
Ubiquitous Acoustic Sensing on Commodity IoT Devices: A Survey
This framework encompasses three layers, i. e., physical layer, core technique layer, and application layer.
Construction of all-in-focus images assisted by depth sensing
A graph-based segmentation algorithm is used to segment the depth map from the depth sensor, and the segmented regions are used to guide a focus algorithm to locate in-focus image blocks from among multi-focus source images to construct the reference all-in-focus image.
