Search Results for author:
Found 47 papers, 18 papers with code
DRA-GRPO: Exploring Diversity-Aware Reward Adjustment for R1-Zero-Like Training of Large Language Models
Our method integrates seamlessly with both GRPO and its variant DR.~GRPO, resulting in $\textit{DRA-GRPO}$ and $\textit{DGA-DR.~GRPO}$.
Monte Carlo Beam Search for Actor-Critic Reinforcement Learning in Continuous Control
Actor-critic methods, like Twin Delayed Deep Deterministic Policy Gradient (TD3), depend on basic noise-based exploration, which can result in less than optimal policy convergence.
FIC-TSC: Learning Time Series Classification with Fisher Information Constraint
However, there is a large consensus that time series data often suffers from domain shifts between training and test sets, which dramatically degrades the classification performance.
How Effective Can Dropout Be in Multiple Instance Learning ?
Due to the gigapixel resolution of WSI, applications of MIL in WSI typically necessitate a two-stage training scheme: first, extract features from the pre-trained backbone and then perform MIL aggregation.
Graph Based Deep Reinforcement Learning Aided by Transformers for Multi-Agent Cooperation
Mission planning for a fleet of cooperative autonomous drones in applications that involve serving distributed target points, such as disaster response, environmental monitoring, and surveillance, is challenging, especially under partial observability, limited communication range, and uncertain environments.
Fire and Smoke Datasets in 20 Years: An In-depth Review
Fire and smoke phenomena pose a significant threat to the natural environment, ecosystems, and global economy, as well as human lives and wildlife.
Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation
Vision-language models (VLMs) such as CLIP demonstrate strong performance but struggle when adapted to downstream tasks.
Anomaly Detection in Cooperative Vehicle Perception Systems under Imperfect Communication
Anomaly detection is a critical requirement for ensuring safety in autonomous driving.
Sequence Complementor: Complementing Transformers For Time Series Forecasting with Learnable Sequences
Since its introduction, the transformer has shifted the development trajectory away from traditional models (e. g., RNN, MLP) in time series forecasting, which is attributed to its ability to capture global dependencies within temporal tokens.
Diffusion Prism: Enhancing Diversity and Morphology Consistency in Mask-to-Image Diffusion
The emergence of generative AI and controllable diffusion has made image-to-image synthesis increasingly practical and efficient.
Multimodal Variational Autoencoder: a Barycentric View
Previous attempts at multimodal VAEs approach this mainly through the lens of experts, aggregating unimodal inference distributions with a product of experts (PoE), a mixture of experts (MoE), or a combination of both.
Geographical Information Alignment Boosts Traffic Analysis via Transpose Cross-attention
This module can efficiently fuse the node feature and geographic position information through a novel Transpose Cross-attention mechanism.
Many-MobileNet: Multi-Model Augmentation for Robust Retinal Disease Classification
In this work, we propose Many-MobileNet, an efficient model fusion strategy for retinal disease classification using lightweight CNN architecture.
RobustFormer: Noise-Robust Pre-training for images and videos
While deep learning models are powerful tools that revolutionized many areas, they are also vulnerable to noise as they rely heavily on learning patterns and features from the exact details of the clean data.
Enhancing Graph Neural Networks in Large-scale Traffic Incident Analysis with Concurrency Hypothesis
The extensive experiments, utilizing real-world data across states and cities in the USA, demonstrate that integrating CP into 12 state-of-the-art GNN architectures leads to significant improvements, with gains ranging from 3% to 13% in F1 score and 1. 3% to 9% in AUC metrics.
Adaptive Data Transport Mechanism for UAV Surveillance Missions in Lossy Environments
Unmanned Aerial Vehicles (UAVs) play an increasingly critical role in Intelligence, Surveillance, and Reconnaissance (ISR) missions such as border patrolling and criminal detection, thanks to their ability to access remote areas and transmit real-time imagery to processing servers.
RBAD: A Dataset and Benchmark for Retinal Vessels Branching Angle Detection
Detecting retinal image analysis, particularly the geometrical features of branching points, plays an essential role in diagnosing eye diseases.
DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classification
Second, we propose two mechanisms to enforce the diversity among the global vectors to be more descriptive of the entire bag: (i) positive instance alignment and (ii) a novel, efficient, and theoretically guaranteed diversification learning paradigm.
SelfReg-UNet: Self-Regularized UNet for Medical Image Segmentation
Although numerous follow-up studies have also been dedicated to improving the performance of standard UNet, few have conducted in-depth analyses of the underlying interest pattern of UNet in medical image segmentation.
Ranked #17 on
Medical Image Segmentation
on Synapse multi-organ CT
TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning
Deep neural networks, including transformers and convolutional neural networks, have significantly improved multivariate time series classification (MTSC).
Imaging Signal Recovery Using Neural Network Priors Under Uncertain Forward Model Parameters
We theoretically demonstrate the convergence of the MA framework, which has a similar complexity with reconstruction under the known forward model parameters.
Motor Focus: Fast Ego-Motion Prediction for Assistive Visual Navigation
Assistive visual navigation systems for visually impaired individuals have become increasingly popular thanks to the rise of mobile computing.
Enhanced Cooperative Perception for Autonomous Vehicles Using Imperfect Communication
To validate our approach, we used the CARLA simulator to create a dataset of annotated videos for different driving scenarios where pedestrian detection is challenging for an AV with compromised vision.
VisionGPT: LLM-Assisted Real-Time Anomaly Detection for Safe Visual Navigation
This paper explores the potential of Large Language Models(LLMs) in zero-shot anomaly detection for safe visual navigation.
FLAME Diffuser: Wildfire Image Synthesis using Mask Guided Diffusion
Specifically, the fusion of Perlin noise in this work significantly improved the quality of synthesized images.
Opinion Dynamics in Social Multiplex Networks with Mono and Bi-directional Interactions in the Presence of Leaders
We further scrutinize the convergence rates of opinion dynamics in networks with one-way versus two-way interactions.
Driving Towards Inclusion: A Systematic Review of AI-powered Accessibility Enhancements for People with Disability in Autonomous Vehicles
This paper provides a comprehensive and, to our knowledge, the first review of inclusive human-computer interaction (HCI) within autonomous vehicles (AVs) and human-driven cars with partial autonomy, emphasizing accessibility and user-centered design principles.
Enhancing Digital Hologram Reconstruction Using Reverse-Attention Loss for Untrained Physics-Driven Deep Learning Models with Uncertain Distance
Untrained Physics-based Deep Learning (DL) methods for digital holography have gained significant attention due to their benefits, such as not requiring an annotated training dataset, and providing interpretability since utilizing the governing laws of hologram formation.
A comprehensive survey of research towards AI-enabled unmanned aerial systems in pre-, active-, and post-wildfire management
Wildfires have emerged as one of the most destructive natural disasters worldwide, causing catastrophic losses in both human lives and forest wildlife.
Quantification of cardiac capillarization in single-immunostained myocardial slices using weakly supervised instance segmentation
Quantitative assessment of cardiac capillarization typically involves double immunostaining of cardiomyocytes (CMs) and capillaries in myocardial slices.
Actuator Trajectory Planning for UAVs with Overhead Manipulator using Reinforcement Learning
In this paper, we investigate the operation of an aerial manipulator system, namely an Unmanned Aerial Vehicle (UAV) equipped with a controllable arm with two degrees of freedom to carry out actuation tasks on the fly.
Obscured Wildfire Flame Detection By Temporal Analysis of Smoke Patterns Captured by Unmanned Aerial Systems
This research paper addresses the challenge of detecting obscured wildfires (when the fire flames are covered by trees, smoke, clouds, and other natural barriers) in real-time using drones equipped only with RGB cameras.
Energy Optimization for HVAC Systems in Multi-VAV Open Offices: A Deep Reinforcement Learning Approach
It takes only a total of 40 minutes for 5 epochs (about 7. 75 minutes per epoch) to train a network with superior performance and covering diverse conditions for its low-complexity architecture; therefore, it easily adapts to changes in the building setups, weather conditions, occupancy rate, etc.
Learning on Bandwidth Constrained Multi-Source Data with MIMO-inspired DPP MAP Inference
A determinant-preserved sparse representation of selected samples is used to perform sample precoding in local sources to be processed by DPP.
RD-DPP: Rate-Distortion Theory Meets Determinantal Point Process to Diversify Learning Data Samples
However, the number of selected samples is restricted to the rank of the kernel matrix implied by the dimensionality of data samples.
Fast Key Points Detection and Matching for Tree-Structured Images
The proposed algorithm is applicable to a variety of tree-structured image matching, but our focus is on dendrites, recently-developed visual identifiers.
DH-GAN: A Physics-driven Untrained Generative Adversarial Network for 3D Microscopic Imaging using Digital Holography
Digital holography is a 3D imaging technique by emitting a laser beam with a plane wavefront to an object and measuring the intensity of the diffracted waveform, called holograms.
Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review
This paper explores Deep Learning (DL) methods that are used or have the potential to be used for traffic video analysis, emphasizing driving safety for both Autonomous Vehicles (AVs) and human-operated vehicles.
Network-level Safety Metrics for Overall Traffic Safety Assessment: A Case Study
To bridge these two perspectives, we define a new set of network-level safety metrics (NSM) to assess the overall safety profile of traffic flow by processing imagery taken by RSU cameras.
Fully-echoed Q-routing with Simulated Annealing Inference for Flying Adhoc Networks
Current networking protocols deem inefficient in accommodating the two key challenges of Unmanned Aerial Vehicle (UAV) networks, namely the network connectivity loss and energy limitations.
Aerial Imagery Pile burn detection using Deep Learning: the FLAME dataset
FLAME (Fire Luminosity Airborne-based Machine learning Evaluation) offers a dataset of aerial images of fires along with methods for fire detection and segmentation which can help firefighters and researchers to develop optimal fire management strategies.
Towards Boosting the Channel Attention in Real Image Denoising : Sub-band Pyramid Attention
We equip the SPA blocks on a network designed for real image denoising.
Deep DIH : Statistically Inferred Reconstruction of Digital In-Line Holography by Deep Learning
Recently, end-to-end deep learning-based methods have been utilized to reconstruct the object wavefront (as a surrogate for the 3D structure of the object) directly from a single-shot in-line digital hologram.
An Autonomous Spectrum Management Scheme for Unmanned Aerial Vehicle Networks in Disaster Relief Operations
This paper studies the problem of spectrum shortage in an unmanned aerial vehicle (UAV) network during critical missions such as wildfire monitoring, search and rescue, and disaster monitoring.
A Solution for Dynamic Spectrum Management in Mission-Critical UAV Networks
In this paper, we study the problem of spectrum scarcity in a network of unmanned aerial vehicles (UAVs) during mission-critical applications such as disaster monitoring and public safety missions, where the pre-allocated spectrum is not sufficient to offer a high data transmission rate for real-time video-streaming.
A Unified Framework for Joint Mobility Prediction and Object Profiling of Drones in UAV Networks
In recent years, using a network of autonomous and cooperative unmanned aerial vehicles (UAVs) without command and communication from the ground station has become more imperative, in particular in search-and-rescue operations, disaster management, and other applications where human intervention is limited.
A Shapley Value Solution to Game Theoretic-based Feature Reduction in False Alarm Detection
False alarm is one of the main concerns in intensive care units and can result in care disruption, sleep deprivation, and insensitivity of care-givers to alarms.
