We Learn Better Road Pothole Detection: from Attention Aggregation to Adversarial Domain Adaptation

• URL: http://arxiv.org/abs/2008.06840v2
• Date: Fri, 11 Dec 2020 10:32:39 GMT
• Title: We Learn Better Road Pothole Detection: from Attention Aggregation to Adversarial Domain Adaptation
• Authors: Rui Fan, Hengli Wang, Mohammud J. Bocus, Ming Liu
• Abstract summary: Road pothole detection results are always subjective, because they depend entirely on the individual experience. Our recently introduced disparity (or inverse depth) transformation algorithm allows better discrimination between damaged and undamaged road areas. We propose a novel attention aggregation (AA) framework, which takes the advantages of different types of attention modules.
• Score: 22.076261078410752
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Manual visual inspection performed by certified inspectors is still the main form of road pothole detection. This process is, however, not only tedious, time-consuming and costly, but also dangerous for the inspectors. Furthermore, the road pothole detection results are always subjective, because they depend entirely on the individual experience. Our recently introduced disparity (or inverse depth) transformation algorithm allows better discrimination between damaged and undamaged road areas, and it can be easily deployed to any semantic segmentation network for better road pothole detection results. To boost the performance, we propose a novel attention aggregation (AA) framework, which takes the advantages of different types of attention modules. In addition, we develop an effective training set augmentation technique based on adversarial domain adaptation, where the synthetic road RGB images and transformed road disparity (or inverse depth) images are generated to enhance the training of semantic segmentation networks. The experimental results demonstrate that, firstly, the transformed disparity (or inverse depth) images become more informative; secondly, AA-UNet and AA-RTFNet, our best performing implementations, respectively outperform all other state-of-the-art single-modal and data-fusion networks for road pothole detection; and finally, the training set augmentation technique based on adversarial domain adaptation not only improves the accuracy of the state-of-the-art semantic segmentation networks, but also accelerates their convergence.

Related papers

• Supervised Image Translation from Visible to Infrared Domain for Object Detection [1.7851018240619703]
  This study aims to learn a translation from visible to infrared imagery, bridging the domain gap between the two modalities. We adopt a two-stage training strategy with a Generative Adversarial Network and an object detection model. Images so generated are used to train standard object detection frameworks including Yolov5, Mask and Faster RCNN.
  arXiv  Detail & Related papers  (2024-08-03T18:51:04Z)
• Unsupervised Domain Adaptive Lane Detection via Contextual Contrast and Aggregation [3.105187291566825]
  Existing lane detection methods exploit a pixel-wise cross-entropy loss to train detection models. Cross-domain context dependency crucial for transferring knowledge across domains remains unexplored in existing lane detection methods. This paper proposes a method of Domain-Adaptive lane detection via Contextual Contrast and Aggregation (DACCA)
  arXiv  Detail & Related papers  (2024-07-18T09:29:02Z)
• ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstruction [29.370142078092375]
  Most advanced unsupervised anomaly detection (UAD) methods rely on modeling feature representations of frozen encoder networks pre-trained on large-scale datasets. We propose a novel epistemic UAD method, namely ReContrast, which optimize the entire network to reduce biases towards the pre-trained image domain. We conduct experiments across two popular industrial defect detection benchmarks and three medical image UAD tasks, which shows our superiority over current state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-06-05T05:21:15Z)
• PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation [100.6343963798169]
  Unsupervised Domain Adaptation (UDA) aims to enhance the generalization of the learned model to other domains. We propose a unified pixel- and patch-wise self-supervised learning framework, called PiPa, for domain adaptive semantic segmentation.
  arXiv  Detail & Related papers  (2022-11-14T18:31:24Z)
• Improving Road Segmentation in Challenging Domains Using Similar Place Priors [25.883291494709688]
  Road segmentation in challenging domains, such as night, snow or rain, is a difficult task. Current approaches boost performance using fine-tuning, domain adaptation, style transfer. Visual Place Recognition (VPR) to find similar but geographically distinct places.
  arXiv  Detail & Related papers  (2022-05-27T17:22:52Z)
• Graph Attention Layer Evolves Semantic Segmentation for Road Pothole Detection: A Benchmark and Algorithms [34.80667966432126]
  Existing road pothole detection approaches can be classified as computer vision-based or machine learning-based. The latter approaches generally address road pothole detection using convolutional neural networks (CNNs) in an end-to-end manner. We propose a novel CNN layer, referred to as graph attention layer (GAL), which can be easily deployed in any existing CNN to optimize image feature representations for semantic segmentation.
  arXiv  Detail & Related papers  (2021-09-06T19:44:50Z)
• Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Images [93.50240389540252]
  Road segmentation from remote sensing images is a challenging task with wide ranges of application potentials. We propose a novel stagewise domain adaptation model called RoadDA to address the domain shift (DS) issue in this field. Experiment results on two benchmarks demonstrate that RoadDA can efficiently reduce the domain gap and outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-08-28T09:29:14Z)
• Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning [62.7588467386166]
  We leverage contrastive learning to bridge the domain gap by aligning the features of structurally similar label patches across domains. Our approach consistently outperforms state-of-the-art unsupervised and semi-supervised methods on two challenging domain adaptive segmentation tasks.
  arXiv  Detail & Related papers  (2021-04-22T13:39:12Z)
• Cross-Domain Similarity Learning for Face Recognition in Unseen Domains [90.35908506994365]
  We introduce a novel cross-domain metric learning loss, which we dub Cross-Domain Triplet (CDT) loss, to improve face recognition in unseen domains. The CDT loss encourages learning semantically meaningful features by enforcing compact feature clusters of identities from one domain. Our method does not require careful hard-pair sample mining and filtering strategy during training.
  arXiv  Detail & Related papers  (2021-03-12T19:48:01Z)
• BoMuDANet: Unsupervised Adaptation for Visual Scene Understanding in Unstructured Driving Environments [54.22535063244038]
  We present an unsupervised adaptation approach for visual scene understanding in unstructured traffic environments. Our method is designed for unstructured real-world scenarios with dense and heterogeneous traffic consisting of cars, trucks, two-and three-wheelers, and pedestrians.
  arXiv  Detail & Related papers  (2020-09-22T08:25:44Z)
• Anchor-free Small-scale Multispectral Pedestrian Detection [88.7497134369344]
  We propose a method for effective and efficient multispectral fusion of the two modalities in an adapted single-stage anchor-free base architecture. We aim at learning pedestrian representations based on object center and scale rather than direct bounding box predictions. Results show our method's effectiveness in detecting small-scaled pedestrians.
  arXiv  Detail & Related papers  (2020-08-19T13:13:01Z)

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.