activity
20172026
most citedDeeperLab: Single-Shot Image Parser

163 citations · 192 across the 10 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV202112 cited

Searching for Efficient Multi-Stage Vision Transformers

Yi-Lun Liao, Sertac Karaman, Vivienne Sze

Vision Transformer (ViT) demonstrates that Transformer for natural language processing can be applied to computer vision tasks and result in comparable performance to convolutional…

cs.CV20213 cited

NetAdaptV2: Efficient Neural Architecture Search with Fast Super-Network Training and Architecture Optimization

Tien-Ju Yang, Yi-Lun Liao, Vivienne Sze

Neural architecture search (NAS) typically consists of three main steps: training a super-network, training and evaluating sampled deep neural networks (DNNs), and training the dis…

cs.CV20193 cited

Design Considerations for Efficient Deep Neural Networks on Processing-in-Memory Accelerators

Tien-Ju Yang, Vivienne Sze

This paper describes various design considerations for deep neural networks that enable them to operate efficiently and accurately on processing-in-memory accelerators. We highligh…

cs.CV2019163 cited

DeeperLab: Single-Shot Image Parser

Tien-Ju Yang, Maxwell D. Collins, Yukun Zhu +6

We present a single-shot, bottom-up approach for whole image parsing. Whole image parsing, also known as Panoptic Segmentation, generalizes the tasks of semantic segmentation for '…

cs.CV2019

FastDepth: Fast Monocular Depth Estimation on Embedded Systems

Diana Wofk, Fangchang Ma, Tien-Ju Yang +2

Depth sensing is a critical function for robotic tasks such as localization, mapping and obstacle detection. There has been a significant and growing interest in depth estimation f…

cs.CV2018

NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications

Tien-Ju Yang, Andrew Howard, Bo Chen +5

This work proposes an algorithm, called NetAdapt, that automatically adapts a pre-trained deep neural network to a mobile platform given a resource budget. While many existing algo…