Search Results for author:
Found 12 papers, 4 papers with code
Temporally Consistent Online Depth Estimation in Dynamic Scenes
We present a framework named Consistent Online Dynamic Depth (CODD) to produce temporally consistent depth estimates in dynamic scenes in an online setting.
Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet
From wearables to powerful smart devices, modern automatic speech recognition (ASR) models run on a variety of edge devices with different computational budgets.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Noisy Training Improves E2E ASR for the Edge
We apply noisy training to improve both dense and sparse state-of-the-art Emformer models and observe consistent WER reduction.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization
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 latency and model accuracy.
Collaborative Training of Acoustic Encoders for Speech Recognition
On-device speech recognition requires training models of different sizes for deploying on devices with various computational budgets.
Accelerating Sparse Deep Neural Networks
We present the design and behavior of Sparse Tensor Cores, which exploit a 2:4 (50%) sparsity pattern that leads to twice the math throughput of dense matrix units.
Memory-efficient Speech Recognition on Smart Devices
Recurrent transducer models have emerged as a promising solution for speech recognition on the current and next generation smart devices.
Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object Segmentation
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 current frame.
Can Temporal Information Help with Contrastive Self-Supervised Learning?
To this end, we present Temporal-aware Contrastive self-supervised learningTaCo, as a general paradigm to enhance video CSL.
TTVOS: Lightweight Video Object Segmentation with Adaptive Template Attention Module and Temporal Consistency Loss
Our template matching method consists of short-term and long-term matching.
Mixed Precision Training
Using this approach, we can reduce the memory consumption of deep learning models by nearly 2x.
Accelerating Deep Convolutional Networks using low-precision and sparsity
To improve the compute efficiency, we focus on achieving high accuracy with extremely low-precision (2-bit) weight networks, and to accelerate the execution time, we aggressively skip operations on zero-values.
