19 citations · 27 across the 9 of their papers we have counts for
9 papers
Domain Generalization Emerges from Dreaming
Hwan Heo, Youngjin Oh, Jaewon Lee +1
Recent studies have proven that DNNs, unlike human vision, tend to exploit texture information rather than shape. Such texture bias is one of the factors for the poor generalizatio…
Building a Performance Model for Deep Learning Recommendation Model Training on GPUs
Zhongyi Lin, Louis Feng, Ehsan K. Ardestani +5
We devise a performance model for GPU training of Deep Learning Recommendation Models (DLRM), whose GPU utilization is low compared to other well-optimized CV and NLP models. We sh…
COX: CUDA on X86 by Exposing Warp-Level Functions to CPUs
Ruobing Han, Jaewon Lee, Jaewoong Sim +1
As CUDA programs become the de facto program among data parallel applications such as high-performance computing or machine learning applications, running CUDA on other platforms h…
Local Texture Estimator for Implicit Representation Function
Jaewon Lee, Kyong Hwan Jin
Recent works with an implicit neural function shed light on representing images in arbitrary resolution. However, a standalone multi-layer perceptron shows limited performance in l…
Point Cloud Augmentation with Weighted Local Transformations
Sihyeon Kim, Sanghyeok Lee, Dasol Hwang +3
Despite the extensive usage of point clouds in 3D vision, relatively limited data are available for training deep neural networks. Although data augmentation is a standard approach…
Supporting CUDA for an extended RISC-V GPU architecture
Ruobing Han, Blaise Tine, Jaewon Lee +2
With the rapid development of scientific computation, more and more researchers and developers are committed to implementing various workloads/operations on different devices. Amon…
First-Generation Inference Accelerator Deployment at Facebook
Michael Anderson, Benny Chen, Stephen Chen +112
In this paper, we provide a deep dive into the deployment of inference accelerators at Facebook. Many of our ML workloads have unique characteristics, such as sparse memory accesse…
A Neural Pre-Conditioning Active Learning Algorithm to Reduce Label Complexity
Seo Taek Kong, Soomin Jeon, Dongbin Na +3
Deep learning (DL) algorithms rely on massive amounts of labeled data. Semi-supervised learning (SSL) and active learning (AL) aim to reduce this label complexity by leveraging unl…
Secure Location-Aware Authentication and Communication for Intelligent Transportation Systems
Nima Shoghi Ghalehshahi, Ramyad Hadidi, Lee Jaewon +6
Intelligent transportation systems (ITS) are expected to effectively create a stand-alone network for secure communication among autonomous agents. In such a dynamic and fast-chang…