# Multi-View Fusion and Distillation for Subgrade Distresses Detection based on 3D-GPR

arXiv: https://arxiv.org/abs/2308.04779 · HTML: https://mlsanity.com/paper/2308.04779/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 50 references that are in the map.
- First posted on arXiv 9 Aug 2023.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [A Structured Self-attentive Sentence Embedding](https://mlsanity.com/paper/1703.03130/) (2017)
- [Composing Text and Image for Image Retrieval - An Empirical Odyssey](https://mlsanity.com/paper/1812.07119/) (2018)
- [Attention Mechanisms in Computer Vision: A Survey](https://mlsanity.com/paper/2111.07624/) (2021)
- [A Survey of Multi-View Representation Learning](https://mlsanity.com/paper/1610.01206/) (2016)
- [Feature Fusion for Online Mutual Knowledge Distillation](https://mlsanity.com/paper/1904.09058/) (2019)
- [Switchable Online Knowledge Distillation](https://mlsanity.com/paper/2209.04996/) (2022)
- [Deep Multi-View Learning using Neuron-Wise Correlation-Maximizing Regularizers](https://mlsanity.com/paper/1904.11151/) (2019)
- [An Improved Convolutional Neural Network System for Automatically Detecting Rebar in GPR Data](https://mlsanity.com/paper/1907.09997/) (2019)

## Built on by (most cited first, 1 of 1)

- [SAM-SP: Self-Prompting Makes SAM Great Again](https://mlsanity.com/paper/2408.12364/) (2024)

## Abstract (arXiv)

The application of 3D ground-penetrating radar (3D-GPR) for subgrade distress detection has gained widespread popularity. To enhance the efficiency and accuracy of detection, pioneering studies have attempted to adopt automatic detection techniques, particularly deep learning. However, existing works typically rely on traditional 1D A-scan, 2D B-scan or 3D C-scan data of the GPR, resulting in either insufficient spatial information or high computational complexity. To address these challenges, we introduce a novel methodology for the subgrade distress detection task by leveraging the multi-view information from 3D-GPR data. Moreover, we construct a real multi-view image dataset derived from the original 3D-GPR data for the detection task, which provides richer spatial information compared to A-scan and B-scan data, while reducing computational complexity compared to C-scan data. Subsequently, we develop a novel Multi-View Vusion and Distillation framework, GPR-MVFD, specifically designed to optimally utilize the multi-view GPR dataset. This framework ingeniously incorporates multi-view distillation and attention-based fusion to facilitate significant feature extraction for subgrade distresses. In addition, a self-adaptive learning mechanism is adopted to stabilize the model training and prevent performance degeneration in each branch. Extensive experiments conducted on this new GPR benchmark demonstrate the effectiveness and efficiency of our proposed framework. Our framework outperforms not only the existing GPR baselines, but also the state-of-the-art methods in the fields of multi-view learning, multi-modal learning, and knowledge distillation. We will release the constructed multi-view GPR dataset with expert-annotated labels and the source codes of the proposed framework.