InversionNet3D: Efficient and Scalable Learning for 3D Full Waveform Inversion

• URL: http://arxiv.org/abs/2103.14158v1
• Date: Thu, 25 Mar 2021 22:24:57 GMT
• Title: InversionNet3D: Efficient and Scalable Learning for 3D Full Waveform Inversion
• Authors: Qili Zeng, Shihang Feng, Brendt Wohlberg, Youzuo Lin
• Abstract summary: In this paper, we present InversionNet3D, an efficient and scalable encoder-decoder network for 3D FWI. The proposed method employs group convolution in the encoder to establish an effective hierarchy for learning information from multiple sources. Experiments on the 3D Kimberlina dataset demonstrate that InversionNet3D achieves lower computational cost and lower memory footprint compared to the baseline.
• Score: 14.574636791985968
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent progress in the use of deep learning for Full Waveform Inversion (FWI) has demonstrated the advantage of data-driven methods over traditional physics-based approaches in terms of reconstruction accuracy and computational efficiency. However, due to high computational complexity and large memory consumption, the reconstruction of 3D high-resolution velocity maps via deep networks is still a great challenge. In this paper, we present InversionNet3D, an efficient and scalable encoder-decoder network for 3D FWI. The proposed method employs group convolution in the encoder to establish an effective hierarchy for learning information from multiple sources while cutting down unnecessary parameters and operations at the same time. The introduction of invertible layers further reduces the memory consumption of intermediate features during training and thus enables the development of deeper networks with more layers and higher capacity as required by different application scenarios. Experiments on the 3D Kimberlina dataset demonstrate that InversionNet3D achieves state-of-the-art reconstruction performance with lower computational cost and lower memory footprint compared to the baseline.

Related papers

• WiNet: Wavelet-based Incremental Learning for Efficient Medical Image Registration [68.25711405944239]
  Deep image registration has demonstrated exceptional accuracy and fast inference. Recent advances have adopted either multiple cascades or pyramid architectures to estimate dense deformation fields in a coarse-to-fine manner. We introduce a model-driven WiNet that incrementally estimates scale-wise wavelet coefficients for the displacement/velocity field across various scales.
  arXiv  Detail & Related papers  (2024-07-18T11:51:01Z)
• Deep Compressed Learning for 3D Seismic Inversion [5.926203312586109]
  We consider the problem of 3D seismic inversion from pre-stack data using a very small number of seismic sources. The proposed solution is based on a combination of compressed-sensing and machine learning frameworks.
  arXiv  Detail & Related papers  (2023-10-31T19:34:26Z)
• Neural Progressive Meshes [54.52990060976026]
  We propose a method to transmit 3D meshes with a shared learned generative space. We learn this space using a subdivision-based encoder-decoder architecture trained in advance on a large collection of surfaces. We evaluate our method on a diverse set of complex 3D shapes and demonstrate that it outperforms baselines in terms of compression ratio and reconstruction quality.
  arXiv  Detail & Related papers  (2023-08-10T17:58:02Z)
• Rethinking IoU-based Optimization for Single-stage 3D Object Detection [103.83141677242871]
  We propose a Rotation-Decoupled IoU (RDIoU) method that can mitigate the rotation-sensitivity issue. Our RDIoU simplifies the complex interactions of regression parameters by decoupling the rotation variable as an independent term.
  arXiv  Detail & Related papers  (2022-07-19T15:35:23Z)
• GLEAM: Greedy Learning for Large-Scale Accelerated MRI Reconstruction [50.248694764703714]
  Unrolled neural networks have recently achieved state-of-the-art accelerated MRI reconstruction. These networks unroll iterative optimization algorithms by alternating between physics-based consistency and neural-network based regularization. We propose Greedy LEarning for Accelerated MRI reconstruction, an efficient training strategy for high-dimensional imaging settings.
  arXiv  Detail & Related papers  (2022-07-18T06:01:29Z)
• Deep Learning for Reduced Order Modelling and Efficient Temporal Evolution of Fluid Simulations [0.0]
  Reduced Order Modelling (ROM) has been widely used to create lower order, computationally inexpensive representations of higher-order dynamical systems. We develop a novel deep learning framework DL-ROM to create a neural network capable of non-linear projections to reduced order states. Our model DL-ROM is able to create highly accurate reconstructions from the learned ROM and is thus able to efficiently predict future time steps by temporally traversing in the learned reduced state.
  arXiv  Detail & Related papers  (2021-07-09T17:21:53Z)
• CovSegNet: A Multi Encoder-Decoder Architecture for Improved Lesion Segmentation of COVID-19 Chest CT Scans [11.946078871080836]
  An automated COVID-19 lesion segmentation scheme is proposed utilizing a highly efficient neural network architecture, namely CovSegNet. Outstanding performances have been achieved in three publicly available datasets that largely outperform other state-of-the-art approaches.
  arXiv  Detail & Related papers  (2020-12-02T19:26:35Z)
• Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks [87.50632573601283]
  We present a novel method for multi-view depth estimation from a single video. Our method achieves temporally coherent depth estimation results by using a novel Epipolar Spatio-Temporal (EST) transformer. To reduce the computational cost, inspired by recent Mixture-of-Experts models, we design a compact hybrid network.
  arXiv  Detail & Related papers  (2020-11-26T04:04:21Z)
• LiteDepthwiseNet: An Extreme Lightweight Network for Hyperspectral Image Classification [9.571458051525768]
  This paper proposes a new network architecture, LiteDepthwiseNet, for hyperspectral image (HSI) classification. LiteDepthwiseNet decomposes standard convolution into depthwise convolution and pointwise convolution, which can achieve high classification performance with minimal parameters. Experiment results on three benchmark hyperspectral datasets show that LiteDepthwiseNet achieves state-of-the-art performance with a very small number of parameters and low computational cost.
  arXiv  Detail & Related papers  (2020-10-15T13:12:17Z)
• Spatial-Spectral Residual Network for Hyperspectral Image Super-Resolution [82.1739023587565]
  We propose a novel spectral-spatial residual network for hyperspectral image super-resolution (SSRNet) Our method can effectively explore spatial-spectral information by using 3D convolution instead of 2D convolution, which enables the network to better extract potential information. In each unit, we employ spatial and temporal separable 3D convolution to extract spatial and spectral information, which not only reduces unaffordable memory usage and high computational cost, but also makes the network easier to train.
  arXiv  Detail & Related papers  (2020-01-14T03:34:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.