Lightweight Convolutional Representations for On-Device Natural Language Processing
The increasing computational and memory complexities of deep neural networks have made it difficult to deploy them on low-resource electronic devices (e.g., mobile phones, tablets, wearables). Practitioners have developed numerous model compression methods to address these concerns, but few have condensed input representations themselves. In this work, we propose a fast, accurate, and lightweight convolutional representation that can be swapped into any neural model and compressed significantly (up to 32x) with a negligible reduction in performance. In addition, we show gains over recurrent representations when considering resource-centric metrics (e.g., model file size, latency, memory usage) on a Samsung Galaxy S9.
Code (0)
등록된 구현이 없습니다.
Tasks
Model CompressionSimilar Papers 제목 키워드 기반
LIDSNet: A Lightweight on-device Intent Detection model using Deep Siamese Network
Intent detection is a crucial task in any Natural Language Understanding (NLU) system and forms the foundation of a task-oriented dialogue system. To build high-quality real-world conversational solutions for edge device…
Intent DetectionNatural Language UnderstandingSentenceTransfer LearningOnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning
Federated learning (FL) has emerged as a promising approach to collaboratively train machine learning models across multiple edge devices while preserving privacy. The success of FL hinges on the efficiency of participat…
Computational EfficiencyFederated LearningImage ClassificationBlazePose: On-device Real-time Body Pose tracking
We present BlazePose, a lightweight convolutional neural network architecture for human pose estimation that is tailored for real-time inference on mobile devices. During inference, the network produces 33 body keypoints…
2D Human Pose Estimation3D Human Pose Estimation3D Pose EstimationPose Estimation+3On-Device Spatial Attention based Sequence Learning Approach for Scene Text Script Identification
Automatic identification of script is an essential component of a multilingual OCR engine. In this paper, we present an efficient, lightweight, real-time and on-device spatial attention based CNN-LSTM network for scene t…
Optical Character Recognition (OCR)Pyramidal Dense Attention Networks for Lightweight Image Super-Resolution
Recently, deep convolutional neural network methods have achieved an excellent performance in image superresolution (SR), but they can not be easily applied to embedded devices due to large memory cost. To solve this pro…
Image Super-ResolutionSuper-Resolution