activity
20172020
most citedDeeperLab: Single-Shot Image Parser

163 citations · 173 across the 5 of their papers we have counts for

collaborators

8 papers

cs.ET2020

Freely scalable and reconfigurable optical hardware for deep learning

Liane Bernstein, Alexander Sludds, Ryan Hamerly +3

As deep neural network (DNN) models grow ever-larger, they can achieve higher accuracy and solve more complex problems. This trend has been enabled by an increase in available comp…

eess.IV20201 cited

Depth Map Estimation of Dynamic Scenes Using Prior Depth Information

James Noraky, Vivienne Sze

Depth information is useful for many applications. Active depth sensors are appealing because they obtain dense and accurate depth maps. However, due to issues that range from powe…

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.RO20194 cited

FSMI: Fast computation of Shannon Mutual Information for information-theoretic mapping

Zhengdong Zhang, Trevor Henderson, Sertac Karaman +1

Exploration tasks are embedded in many robotics applications, such as search and rescue and space exploration. Information-based exploration algorithms aim to find the most informa…

cs.LG2019

MLSys: The New Frontier of Machine Learning Systems

Alexander Ratner, Dan Alistarh, Gustavo Alonso +66

Machine learning (ML) techniques are enjoying rapidly increasing adoption. However, designing and implementing the systems that support ML models in real-world deployments remains…

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 '…