Search Results for author:
Found 7 papers, 4 papers with code
2D-Empowered 3D Object Detection on the Edge
Our main contributions are two-fold: First, we design a 2D-to-3D transformation pipeline that takes as input the point cloud data from LiDAR and 2D bounding boxes from camera that are captured at exactly the same time, and generate 3D bounding boxes efficiently and accurately based on detection results of the previous frames without running 3D detectors.
NFL: Robust Learned Index via Distribution Transformation
Based on the characteristics of the transformed keys, we propose a robust After-Flow Learned Index (AFLI).
A Fast Transformer-based General-Purpose Lossless Compressor
To ease this problem, this paper targets on cutting down the execution time of deep-learning-based compressors.
Variational Nested Dropout
Nested dropout is a variant of dropout operation that is able to order network parameters or features based on the pre-defined importance during training.
Accelerating Monte Carlo Bayesian Inference via Approximating Predictive Uncertainty over the Simplex
In this work, assuming that the exact posterior or a decent approximation is obtained, we propose a generic framework to approximate the output probability distribution induced by model posterior with a parameterized model and in an amortized fashion.
Accelerating Monte Carlo Bayesian Inference via Approximating Predictive Uncertainty over Simplex
In this work, assuming that the exact posterior or a decent approximation is obtained, we propose a generic framework to approximate the output probability distribution induced by model posterior with a parameterized model and in an amortized fashion.
EasyConvPooling: Random Pooling with Easy Convolution for Accelerating Training and Testing
Convolution operations dominate the overall execution time of Convolutional Neural Networks (CNNs).
