Edge-InversionNet: Enabling Efficient Inference of InversionNet on Edge Devices
Not on the map. Why?
Abstract (arXiv)
Seismic full waveform inversion (FWI) is a widely used technique in geophysics for inferring subsurface structures from seismic data. And InversionNet is one of the most successful data-driven machine learning models that is applied to seismic FWI. However, the high computing costs to run InversionNet have made it challenging to be efficiently deployed on edge devices that are usually resource-constrained. Therefore, we propose to employ the structured pruning algorithm to get a lightweight version of InversionNet, which can make an efficient inference on edge devices. And we also made a prototype with Raspberry Pi to run the lightweight InversionNet. Experimental results show that the pruned InversionNet can achieve up to 98.2 % reduction in computing resources with moderate model performance degradation.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 48 of its 66 references that are in the map. First posted on arXiv 14 Oct 2023.
Builds on
48 of 66 references.
References · 48
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
- 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
- 2016Pruning Filters for Efficient ConvNetscited by 1,143
- 2018Federated Learning with Non-IID Datacited by 1,108
- 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 408
- 2019MetaPruning: Meta Learning for Automatic Neural Network Channel Pruningcited by 227
- 2018Memory Efficient Experience Replay for Streaming Learningcited by 128
- 2020PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruningcited by 76
- 2018InversionNet: A Real-Time and Accurate Full Waveform Inversion with CNNs and continuous CRFscited by 61
- 2019SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollerscited by 52
36 more
- 2019Deep-learning inversion: a next generation seismic velocity-model building methodcited by 50
- 2022Revisiting Random Channel Pruning for Neural Network Compressioncited by 50
- 2021OpenFWI: Large-Scale Multi-Structural Benchmark Datasets for Seismic Full Waveform Inversioncited by 44
- 2019Accuracy vs. Efficiency: Achieving Both through FPGA-Implementation Aware Neural Architecture Searchcited by 38
- 2019E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savingscited by 36
- 2020EDD: Efficient Differentiable DNN Architecture and Implementation Co-search for Embedded AI Solutionscited by 36
- 2022Federated Contrastive Learning for Volumetric Medical Image Segmentationcited by 33
- 2018Data-driven Seismic Waveform Inversion: A Study on the Robustness and Generalizationcited by 30
- 2020SparseRT: Accelerating Unstructured Sparsity on GPUs for Deep Learning Inferencecited by 30
- 2021Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a Loopcited by 29
- 2023AutoReP: Automatic ReLU Replacement for Fast Private Network Inferencecited by 29
- 2023LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inferencecited by 27
- 2020Fast OSCAR and OWL Regression via Safe Screening Rulescited by 25
- 2020Enabling On-Device CNN Training by Self-Supervised Instance Filtering and Error Map Pruningcited by 24
- 2020YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Designcited by 24
- 2022A Length Adaptive Algorithm-Hardware Co-design of Transformer on FPGA Through Sparse Attention and Dynamic Pipeliningcited by 22
- 2023Accel-GCN: High-Performance GPU Accelerator Design for Graph Convolution Networkscited by 22
- 2021Enabling On-Device Self-Supervised Contrastive Learning With Selective Data Contrastcited by 21
- 2022Federated Contrastive Learning for Dermatological Disease Diagnosis via On-device Learningcited by 21
- 2020Intermittent Inference with Nonuniformly Compressed Multi-Exit Neural Network for Energy Harvesting Powered Devicescited by 19
- 2022Towards Sparsification of Graph Neural Networkscited by 18
- 2022Distributed Contrastive Learning for Medical Image Segmentationcited by 16
- 2021Decentralized Unsupervised Learning of Visual Representationscited by 15
- 2022Dynamic Sparse Training via Balancing the Exploration-Exploitation Trade-offcited by 15
- 2022An Accelerated Doubly Stochastic Gradient Method with Faster Explicit Model Identificationcited by 14
- 2021InversionNet3D: Efficient and Scalable Learning for 3D Full Waveform Inversioncited by 13
- 2022Synthetic Data Can Also Teach: Synthesizing Effective Data for Unsupervised Visual Representation Learningcited by 12
- 2023An Empirical Study of Large-Scale Data-Driven Full Waveform Inversioncited by 9
- 2022An Intriguing Property of Geophysics Inversioncited by 8
- 2020Pruning Convolutional Neural Networks with Self-Supervisioncited by 7
- 2023PASNet: Polynomial Architecture Search Framework for Two-party Computation-based Secure Neural Network Deploymentcited by 7
- 2023Auto-Linear Phenomenon in Subsurface Imagingcited by 6
- 2022Federated Self-Supervised Contrastive Learning and Masked Autoencoder for Dermatological Disease Diagnosiscited by 5
- 2023Efficient Multitask Learning on Resource-Constrained Systemscited by 4
- 2017Cascaded Region-based Densely Connected Network for Event Detection: A Seismic Applicationcited by 3
- 2022Extremely Weak Supervision Inversion of Multi-physical Propertiescited by 2
Built on by
Citing papers per year: 2024: 2.
2 papers.