A Few-Shot Attention Recurrent Residual U-Net for Crack Segmentation

• URL: http://arxiv.org/abs/2303.01582v1
• Date: Thu, 2 Mar 2023 21:16:17 GMT
• Title: A Few-Shot Attention Recurrent Residual U-Net for Crack Segmentation
• Abstract summary: We present a few-shot learning paradigm for the automated segmentation of road cracks. The framework is based on a U-Net architecture with recurrent residual and attention modules (R2AU-Net) Extensive experiments show that the proposed few-shot R2AU-Net framework outperforms other state-of-the-art networks in terms of Dice and IoU metrics.
• Score: 12.828719975542178
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent studies indicate that deep learning plays a crucial role in the automated visual inspection of road infrastructures. However, current learning schemes are static, implying no dynamic adaptation to users' feedback. To address this drawback, we present a few-shot learning paradigm for the automated segmentation of road cracks, which is based on a U-Net architecture with recurrent residual and attention modules (R2AU-Net). The retraining strategy dynamically fine-tunes the weights of the U-Net as a few new rectified samples are being fed into the classifier. Extensive experiments show that the proposed few-shot R2AU-Net framework outperforms other state-of-the-art networks in terms of Dice and IoU metrics, on a new dataset, named CrackMap, which is made publicly available at https://github.com/ikatsamenis/CrackMap.

Related papers

• nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation [1.5243612944631728]
  We demonstrate that many recent claims fail to hold up when scrutinized for common validation shortcomings. We find that the recipe for state-of-the-art performance is 1) employing CNN-based U-Net models, including ResNet and ConvNeXt variants, 2) using the nnU-Net framework, and 3) scaling models to modern hardware resources.
  arXiv  Detail & Related papers  (2024-04-15T08:19:08Z)
• Faster ISNet for Background Bias Mitigation on Deep Neural Networks [0.4915744683251149]
  Bias or spurious correlations in image backgrounds can impact neural networks, causing shortcut learning and hampering generalization to real-world data. We propose reformulated architectures whose training time becomes independent from this number. We challenge the proposed architectures using synthetic background bias, and COVID-19 detection in chest X-rays, an application that commonly presents background bias.
  arXiv  Detail & Related papers  (2024-01-16T14:49:26Z)
• Designing Deep Networks for Scene Recognition [3.493180651702109]
  We conduct extensive experiments to demonstrate the widely accepted principles in network design may result in dramatic performance differences when the data is altered. This paper presents a novel network design methodology: data-oriented network design. We propose a Deep-Narrow Network and Dilated Pooling module, which improved the scene recognition performance using less than half of the computational resources.
  arXiv  Detail & Related papers  (2023-03-13T18:28:06Z)
• DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation [99.88539409432916]
  We study the unsupervised domain adaptation (UDA) process. We propose a novel UDA method, DAFormer, based on the benchmark results. DAFormer significantly improves the state-of-the-art performance by 10.8 mIoU for GTA->Cityscapes and 5.4 mIoU for Synthia->Cityscapes.
  arXiv  Detail & Related papers  (2021-11-29T19:00:46Z)
• PDFNet: Pointwise Dense Flow Network for Urban-Scene Segmentation [0.0]
  We propose a novel lightweight architecture named point-wise dense flow network (PDFNet) In PDFNet, we employ dense, residual, and multiple shortcut connections to allow a smooth gradient flow to all parts of the network. Our method significantly outperforms baselines in capturing small classes and in few-data regimes.
  arXiv  Detail & Related papers  (2021-09-21T10:39:46Z)
• Unsupervised Learning of 3D Object Categories from Videos in the Wild [75.09720013151247]
  We focus on learning a model from multiple views of a large collection of object instances. We propose a new neural network design, called warp-conditioned ray embedding (WCR), which significantly improves reconstruction. Our evaluation demonstrates performance improvements over several deep monocular reconstruction baselines on existing benchmarks.
  arXiv  Detail & Related papers  (2021-03-30T17:57:01Z)
• Local Critic Training for Model-Parallel Learning of Deep Neural Networks [94.69202357137452]
  We propose a novel model-parallel learning method, called local critic training. We show that the proposed approach successfully decouples the update process of the layer groups for both convolutional neural networks (CNNs) and recurrent neural networks (RNNs) We also show that trained networks by the proposed method can be used for structural optimization.
  arXiv  Detail & Related papers  (2021-02-03T09:30:45Z)
• Few-Shot Classification with Feature Map Reconstruction Networks [41.50028437830414]
  We introduce a novel mechanism for few-shot classification by regressing directly from support features to query features in closed form. The resulting Feature Map Reconstruction Networks are both more performant and computationally efficient than previous approaches.
  arXiv  Detail & Related papers  (2020-12-02T20:19:09Z)
• Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks [78.65792427542672]
  Dynamic Graph Network (DG-Net) is a complete directed acyclic graph, where the nodes represent convolutional blocks and the edges represent connection paths. Instead of using the same path of the network, DG-Net aggregates features dynamically in each node, which allows the network to have more representation ability.
  arXiv  Detail & Related papers  (2020-10-02T16:50:26Z)
• BiO-Net: Learning Recurrent Bi-directional Connections for Encoder-Decoder Architecture [82.64881585566825]
  We present a novel Bi-directional O-shape network (BiO-Net) that reuses the building blocks in a recurrent manner without introducing any extra parameters. Our method significantly outperforms the vanilla U-Net as well as other state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-07-01T05:07:49Z)
• A Model-driven Deep Neural Network for Single Image Rain Removal [52.787356046951494]
  We propose a model-driven deep neural network for the task, with fully interpretable network structures. Based on the convolutional dictionary learning mechanism for representing rain, we propose a novel single image deraining model. All the rain kernels and operators can be automatically extracted, faithfully characterizing the features of both rain and clean background layers.
  arXiv  Detail & Related papers  (2020-05-04T09:13:25Z)

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.