996 citations · 1.1k across the 10 of their papers we have counts for
12 papers
Temporally Consistent Online Depth Estimation in Dynamic Scenes
Zhaoshuo Li, Wei Ye, Dilin Wang +4
Temporally consistent depth estimation is crucial for online applications such as augmented reality. While stereo depth estimation has received substantial attention as a promising…
Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet
Haichuan Yang, Yuan Shangguan, Dilin Wang +6
From wearables to powerful smart devices, modern automatic speech recognition (ASR) models run on a variety of edge devices with different computational budgets. To navigate the Pa…
Collaborative Training of Acoustic Encoders for Speech Recognition
Varun Nagaraja, Yangyang Shi, Ganesh Venkatesh +3
On-device speech recognition requires training models of different sizes for deploying on devices with various computational budgets. When building such different models, we can be…
Noisy Training Improves E2E ASR for the Edge
Dilin Wang, Yuan Shangguan, Haichuan Yang +6
Automatic speech recognition (ASR) has become increasingly ubiquitous on modern edge devices. Past work developed streaming End-to-End (E2E) all-neural speech recognizers that can…
Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization
David Eriksson, Pierce I-Jen Chuang, Samuel Daulton +7
When tuning the architecture and hyperparameters of large machine learning models for on-device deployment, it is desirable to understand the optimal trade-offs between on-device l…
Accelerating Sparse Deep Neural Networks
Asit Mishra, Jorge Albericio Latorre, Jeff Pool +5
As neural network model sizes have dramatically increased, so has the interest in various techniques to reduce their parameter counts and accelerate their execution. An active area…
Memory-efficient Speech Recognition on Smart Devices
Ganesh Venkatesh, Alagappan Valliappan, Jay Mahadeokar +4
Recurrent transducer models have emerged as a promising solution for speech recognition on the current and next generation smart devices. The transducer models provide competitive…
Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object Segmentation
Hyojin Park, Jayeon Yoo, Seohyeong Jeong +2
Current state-of-the-art approaches for Semi-supervised Video Object Segmentation (Semi-VOS) propagates information from previous frames to generate segmentation mask for the curre…
Can Temporal Information Help with Contrastive Self-Supervised Learning?
Yutong Bai, Haoqi Fan, Ishan Misra +6
Leveraging temporal information has been regarded as essential for developing video understanding models. However, how to properly incorporate temporal information into the recent…
TTVOS: Lightweight Video Object Segmentation with Adaptive Template Attention Module and Temporal Consistency Loss
Hyojin Park, Ganesh Venkatesh, Nojun Kwak
Semi-supervised video object segmentation (semi-VOS) is widely used in many applications. This task is tracking class-agnostic objects from a given target mask. For doing this, var…
Mixed Precision Training
Paulius Micikevicius, Sharan Narang, Jonah Alben +8
Deep neural networks have enabled progress in a wide variety of applications. Growing the size of the neural network typically results in improved accuracy. As model sizes grow, th…
Accelerating Deep Convolutional Networks using low-precision and sparsity
Ganesh Venkatesh, Eriko Nurvitadhi, Debbie Marr
We explore techniques to significantly improve the compute efficiency and performance of Deep Convolution Networks without impacting their accuracy. To improve the compute efficien…