Search Results for author:
Found 19 papers, 8 papers with code
Anytime-Lidar: Deadline-aware 3D Object Detection
We propose a scheduling algorithm, which intelligently selects the subset of the components to make effective time and accuracy trade-off on the fly.
A Unified Knowledge Distillation Framework for Deep Directed Graphical Models
Moreover, our method achieves good performance for discriminative deep DGMs compression.
On Orthogonality Constraints for Transformers
Orthogonality constraints encourage matrices to be orthogonal for numerical stability.
CrossRoI: Cross-camera Region of Interest Optimization for Efficient Real Time Video Analytics at Scale
Video cameras are pervasively deployed in city scale for public good or community safety (i. e. traffic monitoring or suspected person tracking).
Deep Compressive Offloading: Speeding Up Neural Network Inference by Trading Edge Computation for Network Latency
With comprehensive evaluations, our system can consistently reduce end-to-end latency by 2× to 4× with 1% accuracy loss, compared to state-of-the-art neural network offloading systems.
Scheduling Real-time Deep Learning Services as Imprecise Computations
The paper presents an efficient real-time scheduling algorithm for intelligent real-time edge services, defined as those that perform machine intelligence tasks, such as voice recognition, LIDAR processing, or machine vision, on behalf of local embedded devices that are themselves unable to support extensive computations.
ControlVAE: Tuning, Analytical Properties, and Performance Analysis
ControlVAE is a new variational autoencoder (VAE) framework that combines the automatic control theory with the basic VAE to stabilize the KL-divergence of VAE models to a specified value.
A Spherical Hidden Markov Model for Semantics-Rich Human Mobility Modeling
We propose SHMM, a multi-modal spherical hidden Markov model for semantics-rich human mobility modeling.
DynamicVAE: Decoupling Reconstruction Error and Disentangled Representation Learning
Existing methods, such as $\beta$-VAE and FactorVAE, assign a large weight to the KL-divergence term in the objective function, leading to high reconstruction errors for the sake of better disentanglement.
Semi-supervised Hypergraph Node Classification on Hypergraph Line Expansion
Previous hypergraph expansions are solely carried out on either vertex level or hyperedge level, thereby missing the symmetric nature of data co-occurrence, and resulting in information loss.
ControlVAE: Controllable Variational Autoencoder
Variational Autoencoders (VAE) and their variants have been widely used in a variety of applications, such as dialog generation, image generation and disentangled representation learning.
paper2repo: GitHub Repository Recommendation for Academic Papers
Motivated by this trend, we describe a novel item-item cross-platform recommender system, $\textit{paper2repo}$, that recommends relevant repositories on GitHub that match a given paper in an academic search system such as Microsoft Academic.
Revisiting Over-smoothing in Deep GCNs
Oversmoothing has been assumed to be the major cause of performance drop in deep graph convolutional networks (GCNs).
Hierarchical Overlapping Belief Estimation by Structured Matrix Factorization
In the synthetic dataset, our model reduces error by 40%.
STFNets: Learning Sensing Signals from the Time-Frequency Perspective with Short-Time Fourier Neural Networks
IoT applications, however, often measure physical phenomena, where the underlying physics (such as inertia, wireless signal propagation, or the natural frequency of oscillation) are fundamentally a function of signal frequencies, offering better features in the frequency domain.
FastDeepIoT: Towards Understanding and Optimizing Neural Network Execution Time on Mobile and Embedded Devices
We show that changing neural network size does not proportionally affect performance attributes of interest, such as execution time.
RDeepSense: Reliable Deep Mobile Computing Models with Uncertainty Estimations
Recent advances in deep learning have led various applications to unprecedented achievements, which could potentially bring higher intelligence to a broad spectrum of mobile and ubiquitous applications.
DeepIoT: Compressing Deep Neural Network Structures for Sensing Systems with a Compressor-Critic Framework
It is thus able to shorten execution time by 71. 4% to 94. 5%, and decrease energy consumption by 72. 2% to 95. 7%.
DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing
For many mobile applications, it is hard to find a distribution that exactly describes the noise in practice.
