Search Results for author:
Found 39 papers, 20 papers with code
Globally Optimal and Efficient Vanishing Point Estimation in Atlanta World
In Atlanta world, given a set of image lines, we aim to cluster them by the unknown-but-sought VPs whose number is unknown.
Physics-Inspired Distributed Radio Map Estimation
While existing deep learning based methods conduct RME given spectrum measurements gathered from dispersed sensors in the region of interest, they rely on centralized data at a fusion center, which however raises critical concerns on data privacy leakages and high communication overloads.
Efficient Transmission of Radiomaps via Physics-Enhanced Semantic Communications
To enable real-time, distributed spectrum management, particularly in the scenarios with unstable and dynamic environments, the efficient transmission of spectrum coverage information for radiomaps from edge devices to the central server emerges as a critical problem.
MonSter: Marry Monodepth to Stereo Unleashes Power
The refined monodepth is in turn guides stereo effectively at ill-posed regions.
Quantum Cognition-Inspired EEG-based Recommendation via Graph Neural Networks
Current recommendation systems recommend goods by considering users' historical behaviors, social relations, ratings, and other multi-modals.
ConDo: Continual Domain Expansion for Absolute Pose Regression
Instead of applying standard unsupervised domain adaptation methods which are ineffective for APR, ConDo effectively learns from unlabeled data by distilling knowledge from scene-agnostic localization methods.
RoMeO: Robust Metric Visual Odometry
We propose Robust Metric Visual Odometry (RoMeO), a novel method that resolves these issues leveraging priors from pre-trained depth models.
Spectrum Prediction via Graph Structure Learning
Empowered by the graph structure estimator, graph convolutional networks are fueled to effectively extract the correlations in the frequency domain, followed by gated recurrent unit networks to further extract the temporal correlations of each band.
L-MAGIC: Language Model Assisted Generation of Images with Coherence
However, the lack of global scene layout priors leads to subpar outputs with duplicated objects (e. g., multiple beds in a bedroom) or requires time-consuming human text inputs for each view.
Leveraging Unknown Objects to Construct Labeled-Unlabeled Meta-Relationships for Zero-Shot Object Navigation
Furthermore, we propose the label-wise meta-correlation module (LWMCM) to harness relationships among objects with and without labels, and obtain enhanced objects information.
Distributed Swarm Learning for Edge Internet of Things
The rapid growth of Internet of Things (IoT) has led to the widespread deployment of smart IoT devices at wireless edge for collaborative machine learning tasks, ushering in a new era of edge learning.
Security Risks Concerns of Generative AI in the IoT
In an era where the Internet of Things (IoT) intersects increasingly with generative Artificial Intelligence (AI), this article scrutinizes the emergent security risks inherent in this integration.
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation
For metric depth estimation, we show that the key to a zero-shot single-view model lies in resolving the metric ambiguity from various camera models and large-scale data training.
Ranked #1 on
Surface Normals Estimation
on NYU Depth v2
(using extra training data)
RobustSentEmbed: Robust Sentence Embeddings Using Adversarial Self-Supervised Contrastive Learning
In this paper, we introduce RobustSentEmbed, a self-supervised sentence embedding framework designed to improve both generalization and robustness in diverse text representation tasks and against a diverse set of adversarial attacks.
GIM: Learning Generalizable Image Matcher From Internet Videos
Given an architecture, GIM first trains it on standard domain-specific datasets and then combines it with complementary matching methods to create dense labels on nearby frames of novel videos.
Ranked #1 on
Image Matching
on ZEB
I can't see it but I can Fine-tune it: On Encrypted Fine-tuning of Transformers using Fully Homomorphic Encryption
In today's machine learning landscape, fine-tuning pretrained transformer models has emerged as an essential technique, particularly in scenarios where access to task-aligned training data is limited.
MedBlindTuner: Towards Privacy-preserving Fine-tuning on Biomedical Images with Transformers and Fully Homomorphic Encryption
Advancements in machine learning (ML) have significantly revolutionized medical image analysis, prompting hospitals to rely on external ML services.
LiSA: LiDAR Localization with Semantic Awareness
In SCR a scene is represented as a neural network which outputs the world coordinates for each point in the input point cloud.
CorresNeRF: Image Correspondence Priors for Neural Radiance Fields
We present CorresNeRF, a novel method that leverages image correspondence priors computed by off-the-shelf methods to supervise NeRF training.
E2PNet: Event to Point Cloud Registration with Spatio-Temporal Representation Learning
While registration of 2D RGB images to 3D point clouds is a long-standing problem in computer vision, no prior work studies 2D-3D registration for event cameras.
LDM3D-VR: Latent Diffusion Model for 3D VR
Our models are fine-tuned from existing pretrained models on datasets containing panoramic/high-resolution RGB images, depth maps and captions.
Graph Convolutional Network with Connectivity Uncertainty for EEG-based Emotion Recognition
To address these challenges, this study introduces the distribution-based uncertainty method to represent spatial dependencies and temporal-spectral relativeness in EEG signals based on Graph Convolutional Network (GCN) architecture that adaptively assigns weights to functional aggregate node features, enabling effective long-path capturing while mitigating over-smoothing phenomena.
CLNeRF: Continual Learning Meets NeRF
The source code, and the WAT dataset are available at https://github. com/IntelLabs/CLNeRF.
Adaptive pruning-based Newton's method for distributed learning
Newton's method leverages curvature information to boost performance, and thus outperforms first-order methods for distributed learning problems.
Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image
State-of-the-art (SOTA) monocular metric depth estimation methods can only handle a single camera model and are unable to perform mixed-data training due to the metric ambiguity.
Ranked #28 on
Monocular Depth Estimation
on NYU-Depth V2
(using extra training data)
Enhancing Worker Recruitment in Collaborative Mobile Crowdsourcing: A Graph Neural Network Trust Evaluation Approach
The worker recruitment problem is modeled as an Undirected Complete Recruitment Graph (UCRG), for which a specific Tabu Search Recruitment (TSR) algorithm solution is proposed.
Online Continual Learning Without the Storage Constraint
In this paper, we target such applications, investigating the online continual learning problem under relaxed storage constraints and limited computational budgets.
Evaluation of Test-Time Adaptation Under Computational Time Constraints
To address this issue, we propose a more realistic evaluation protocol for TTA methods, where data is received in an online fashion from a constant-speed data stream, thereby accounting for the method's adaptation speed.
SimCS: Simulation for Domain Incremental Online Continual Segmentation
This work explores the problem of Online Domain-Incremental Continual Segmentation (ODICS), where the model is continually trained over batches of densely labeled images from different domains, with limited computation and no information about the task boundaries.
Improving information retention in large scale online continual learning
The typical approach to address information retention (the ability to retain previous knowledge) is keeping a replay buffer of a fixed size and computing gradients using a mixture of new data and the replay buffer.
AED: An black-box NLP classifier model attacker
A transparency and robust model is always demanded in high-stakes domains where reliability and safety are enforced, such as healthcare and finance.
Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data
We argue that "online" continual learning, where data is a single continuous stream without task boundaries, enables evaluating both information retention and online learning efficacy.
Generative Adversarial Networks: A Survey Towards Private and Secure Applications
Generative Adversarial Networks (GAN) have promoted a variety of applications in computer vision, natural language processing, etc.
Collaborative City Digital Twin For Covid-19 Pandemic: A Federated Learning Solution
In this work, we propose a collaborative city digital twin based on FL, a novel paradigm that allowing multiple city DT to share the local strategy and status in a timely manner.
Adversarial Privacy Preserving Graph Embedding against Inference Attack
In this paper, we propose Adversarial Privacy Graph Embedding (APGE), a graph adversarial training framework that integrates the disentangling and purging mechanisms to remove users' private information from learned node representations.
Consensus Maximization Tree Search Revisited
First, we show that the consensus maximization tree structure used previously actually contains paths that connect nodes at both adjacent and non-adjacent levels.
Practical optimal registration of terrestrial LiDAR scan pairs
Point cloud registration is a fundamental problem in 3D scanning.
Deterministic consensus maximization with biconvex programming
In this paper, we propose an efficient deterministic optimization algorithm for consensus maximization.
Robust Fitting in Computer Vision: Easy or Hard?
Robust model fitting plays a vital role in computer vision, and research into algorithms for robust fitting continues to be active.
