Search Results for author:
Found 42 papers, 15 papers with code
Online 3D Bin Packing with Constrained Deep Reinforcement Learning
We solve a challenging yet practically useful variant of 3D Bin Packing Problem (3D-BPP).
Location-aware Single Image Reflection Removal
It is beneficial to strong reflection detection and substantially improves the quality of reflection removal results.
YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs
Performance of object detection models has been growing rapidly on two major fronts, model accuracy and efficiency.
Active Boundary Loss for Semantic Segmentation
This paper proposes a novel active boundary loss for semantic segmentation.
Multi-level Knowledge Distillation via Knowledge Alignment and Correlation
While it is important to transfer the full knowledge from teacher to student, we introduce the Multi-level Knowledge Distillation (MLKD) by effectively considering both knowledge alignment and correlation.
Unsupervised Image Generation with Infinite Generative Adversarial Networks
Image generation has been heavily investigated in computer vision, where one core research challenge is to generate images from arbitrarily complex distributions with little supervision.
Adaptive Local Basis Functions for Shape Completion
Quantitative and qualitative experiments demonstrate that our method outperforms the state-of-the-art methods in shape completion, detail preservation, generalization to unseen geometries, and computational cost.
Deep Geometric Distillation Network for Compressive Sensing MRI
Compressed sensing (CS) is an efficient method to reconstruct MR image from small sampled data in $k$-space and accelerate the acquisition of MRI.
DeepWarp: DNN-based Nonlinear Deformation
DeepWarp is an efficient and highly re-usable deep neural network (DNN) based nonlinear deformable simulation framework.
Graphics
An Interpretable MRI Reconstruction Network with Two-grid-cycle Correction and Geometric Prior Distillation
Although existing deep learning compressed-sensing-based Magnetic Resonance Imaging (CS-MRI) methods have achieved considerably impressive performance, explainability and generalizability continue to be challenging for such methods since the transition from mathematical analysis to network design not always natural enough, often most of them are not flexible enough to handle multi-sampling-ratio reconstruction assignments.
DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Sampling
A classic mechanism for this purpose is DP-SGD, which is a differentially private version of the stochastic gradient descent (SGD) optimizer commonly used for DNN training.
Nest-DGIL: Nesterov-optimized Deep Geometric Incremental Learning for CS Image Reconstruction
In the image restoration step, a cascade geometric incremental learning module is designed to compensate for missing texture information from different geometric spectral decomposition domains.
AutoGMap: Learning to Map Large-scale Sparse Graphs on Memristive Crossbars
But the exploration of large-scale sparse graph computing on processing-in-memory (PIM) platforms (typically with memristive crossbars) is still in its infancy.
Convex Optimization for Linear Query Processing under Approximate Differential Privacy
This paper points out that under ($\epsilon$, $\delta$)-differential privacy, the optimal solution of the above constrained optimization problem in search of a suitable strategy can be found, rather surprisingly, by solving a simple and elegant convex optimization program.
Development of a 3D tongue motion visualization platform based on ultrasound image sequences
This article describes the development of a platform designed to visualize the 3D motion of the tongue using ultrasound image sequences.
Contour-based 3d tongue motion visualization using ultrasound image sequences
This article describes a contour-based 3D tongue deformation visualization framework using B-mode ultrasound image sequences.
Collecting and Analyzing Data from Smart Device Users with Local Differential Privacy
Organizations with a large user base, such as Samsung and Google, can potentially benefit from collecting and mining users' data.
Databases
Homogeneous Network Embedding for Massive Graphs via Reweighted Personalized PageRank
Given an input graph G and a node v in G, homogeneous network embedding (HNE) maps the graph structure in the vicinity of v to a compact, fixed-dimensional feature vector.
Collecting and Analyzing Multidimensional Data with Local Differential Privacy
Motivated by this, we first propose novel LDP mechanisms for collecting a numeric attribute, whose accuracy is at least no worse (and usually better) than existing solutions in terms of worst-case noise variance.
DBRec: Dual-Bridging Recommendation via Discovering Latent Groups
In addition, we propose to jointly learn user-user group (item-item group) hierarchies, so that we can effectively discover latent groups and learn compact user/item representations.
Fine-Grained Propaganda Detection with Fine-Tuned BERT
This paper presents the winning solution of the Fragment Level Classification (FLC) task in the Fine Grained Propaganda Detection competition at the NLP4IF{'}19 workshop.
Double cycle-consistent generative adversarial network for unsupervised conditional generation
We enforce the encoder and the generator of GAN to form an encoder-generator pair in addition to the generator-encoder pair, which enables us to avoid the low-diversity generation and the triviality of latent features.
Realtime Index-Free Single Source SimRank Processing on Web-Scale Graphs
Given a graph G and a node u in G, a single source SimRank query evaluates the similarity between u and every node v in G. Existing approaches to single source SimRank computation incur either long query response time, or expensive pre-computation, which needs to be performed again whenever the graph G changes.
Compressing Large-Scale Transformer-Based Models: A Case Study on BERT
Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks.
DCAF: A Dynamic Computation Allocation Framework for Online Serving System
These stages usually allocate resource manually with specific computing power budgets, which requires the serving configuration to adapt accordingly.
Second-order Neural Network Training Using Complex-step Directional Derivative
We believe our method will inspire a wide-range of new algorithms for deep learning and numerical optimization.
In-game Residential Home Planning via Visual Context-aware Global Relation Learning
In this paper, we propose an effective global relation learning algorithm to recommend an appropriate location of a building unit for in-game customization of residential home complex.
Effective and Scalable Clustering on Massive Attributed Graphs
Given a graph G where each node is associated with a set of attributes, and a parameter k specifying the number of output clusters, k-attributed graph clustering (k-AGC) groups nodes in G into k disjoint clusters, such that nodes within the same cluster share similar topological and attribute characteristics, while those in different clusters are dissimilar.
Training Massive Deep Neural Networks in a Smart Contract: A New Hope
However, training / running large-scale DNNs as part of a smart contract is infeasible on today's blockchain platforms, due to two fundamental design issues of these platforms.
Distributed Skellam Mechanism: a Novel Approach to Federated Learning with Differential Privacy
We point out a major challenge in this problem setting: that common mechanisms for enforcing DP in deep learning, which require injecting \textit{real-valued noise}, are fundamentally incompatible with MPC, which exchanges \textit{finite-field integers} among the participants.
Pose Guided Image Generation from Misaligned Sources via Residual Flow Based Correction
However, as source images are often misaligned due to the large disparities among the camera settings, strong assumptions have been made in the past with respect to the camera(s) or/and the object in interest, limiting the application of such techniques.
Suboptimal Safety-Critical Control for Continuous Systems Using Prediction-Correction Online Optimization
This paper investigates the control barrier function (CBF) based safety-critical control for continuous nonlinear control affine systems using the more efficient online algorithms through time-varying optimization.
TPA-Net: Generate A Dataset for Text to Physics-based Animation
Recent breakthroughs in Vision-Language (V&L) joint research have achieved remarkable results in various text-driven tasks.
Skellam Mixture Mechanism: a Novel Approach to Federated Learning with Differential Privacy
Deep neural networks have strong capabilities of memorizing the underlying training data, which can be a serious privacy concern.
Contrastive Representation Disentanglement for Clustering
We conduct a theoretical analysis of the proposed loss and highlight how it assigns different weights to negative samples during the process of disentangling the feature representation.
Model-Assisted Probabilistic Safe Adaptive Control With Meta-Bayesian Learning
Specifically, with the help of CBF method, we learn the inherent and external uncertainties by a unified adaptive Bayesian linear regression (ABLR) model, which consists of a forward neural network (NN) and a Bayesian output layer.
PRISTA-Net: Deep Iterative Shrinkage Thresholding Network for Coded Diffraction Patterns Phase Retrieval
This network utilizes a learnable nonlinear transformation to address the proximal-point mapping sub-problem associated with the sparse priors, and an attention mechanism to focus on phase information containing image edges, textures, and structures.
A Multi-scale Generalized Shrinkage Threshold Network for Image Blind Deblurring in Remote Sensing
Furthermore, we propose a deep proximal mapping module in the image domain, which combines a generalized shrinkage threshold with a multi-scale prior feature extraction block.
PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics
We introduce PhysGaussian, a new method that seamlessly integrates physically grounded Newtonian dynamics within 3D Gaussians to achieve high-quality novel motion synthesis.
PIE-NeRF: Physics-based Interactive Elastodynamics with NeRF
We show that physics-based simulations can be seamlessly integrated with NeRF to generate high-quality elastodynamics of real-world objects.
Gaussian Splashing: Dynamic Fluid Synthesis with Gaussian Splatting
We demonstrate the feasibility of integrating physics-based animations of solids and fluids with 3D Gaussian Splatting (3DGS) to create novel effects in virtual scenes reconstructed using 3DGS.
VR-GS: A Physical Dynamics-Aware Interactive Gaussian Splatting System in Virtual Reality
As consumer Virtual Reality (VR) and Mixed Reality (MR) technologies gain momentum, there's a growing focus on the development of engagements with 3D virtual content.
