output
20142021
most citedVoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection

318 citations

Showing 2020Show all

5 papers · 1 filter

cs.CL2020

Frame-level SpecAugment for Deep Convolutional Neural Networks in Hybrid ASR Systems

Xinwei Li, Yuanyuan Zhang, Xiaodan Zhuang +1

Inspired by SpecAugment -- a data augmentation method for end-to-end ASR systems, we propose a frame-level SpecAugment method (f-SpecAugment) to improve the performance of deep con…

cs.LG20201 cited

SapAugment: Learning A Sample Adaptive Policy for Data Augmentation

Ting-Yao Hu, Ashish Shrivastava, Jen-Hao Rick Chang +5

Data augmentation methods usually apply the same augmentation (or a mix of them) to all the training samples. For example, to perturb data with noise, the noise is sampled from a N…

cs.LG202020 cited

AdaScale SGD: A User-Friendly Algorithm for Distributed Training

Tyler B. Johnson, Pulkit Agrawal, Haijie Gu +1

When using large-batch training to speed up stochastic gradient descent, learning rates must adapt to new batch sizes in order to maximize speed-ups and preserve model quality. Re-…

cs.LG202042 cited

Learning to Branch for Multi-Task Learning

Pengsheng Guo, Chen-Yu Lee, Daniel Ulbricht

Training multiple tasks jointly in one deep network yields reduced latency during inference and better performance over the single-task counterpart by sharing certain layers of a n…

cs.LG20208 cited

Privacy-preserving Learning via Deep Net Pruning

Yangsibo Huang, Yushan Su, Sachin Ravi +3

This paper attempts to answer the question whether neural network pruning can be used as a tool to achieve differential privacy without losing much data utility. As a first step to…