RADA: Robust Adversarial Data Augmentation for Camera Localization in Challenging Weather

• URL: http://arxiv.org/abs/2112.02469v1
• Date: Sun, 5 Dec 2021 03:49:11 GMT
• Title: RADA: Robust Adversarial Data Augmentation for Camera Localization in Challenging Weather
• Authors: Jialu Wang, Muhamad Risqi U. Saputra, Chris Xiaoxuan Lu, Niki Trigon, and Andrew Markham
• Abstract summary: We present RADA, a system that learns to generate minimal image perturbations that are still capable of perplexing the network. We show that our method achieves up to two times higher accuracy than the SOTA localization models when tested on unseen' challenging weather conditions.
• Score: 21.198320891744366
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Camera localization is a fundamental and crucial problem for many robotic applications. In recent years, using deep-learning for camera-based localization has become a popular research direction. However, they lack robustness to large domain shifts, which can be caused by seasonal or illumination changes between training and testing data sets. Data augmentation is an attractive approach to tackle this problem, as it does not require additional data to be provided. However, existing augmentation methods blindly perturb all pixels and therefore cannot achieve satisfactory performance. To overcome this issue, we proposed RADA, a system whose aim is to concentrate on perturbing the geometrically informative parts of the image. As a result, it learns to generate minimal image perturbations that are still capable of perplexing the network. We show that when these examples are utilized as augmentation, it greatly improves robustness. We show that our method outperforms previous augmentation techniques and achieves up to two times higher accuracy than the SOTA localization models (e.g., AtLoc and MapNet) when tested on `unseen' challenging weather conditions.

Related papers

• Quanv4EO: Empowering Earth Observation by means of Quanvolutional Neural Networks [62.12107686529827]
  This article highlights a significant shift towards leveraging quantum computing techniques in processing large volumes of remote sensing data. The proposed Quanv4EO model introduces a quanvolution method for preprocessing multi-dimensional EO data. Key findings suggest that the proposed model not only maintains high precision in image classification but also shows improvements of around 5% in EO use cases.
  arXiv  Detail & Related papers  (2024-07-24T09:11:34Z)
• VICAN: Very Efficient Calibration Algorithm for Large Camera Networks [49.17165360280794]
  We introduce a novel methodology that extends Pose Graph Optimization techniques. We consider the bipartite graph encompassing cameras, object poses evolving dynamically, and camera-object relative transformations at each time step. Our framework retains compatibility with traditional PGO solvers, but its efficacy benefits from a custom-tailored optimization scheme.
  arXiv  Detail & Related papers  (2024-03-25T17:47:03Z)
• Your Image is My Video: Reshaping the Receptive Field via Image-To-Video Differentiable AutoAugmentation and Fusion [35.88039888482076]
  We introduce the first Differentiable Augmentation Search method (DAS) to generate variations of images that can be processed as videos. DAS is extremely fast and flexible, allowing the search on very large search spaces in less than a GPU day. We leverage DAS to guide the reshaping of the spatial receptive field by selecting task-dependant transformations.
  arXiv  Detail & Related papers  (2024-03-22T13:27:57Z)
• ShapeAug: Occlusion Augmentation for Event Camera Data [13.634866461329224]
  We present a novel event data augmentation approach for Dynamic Vision Sensors (DVSs) We introduce synthetic events for randomly moving objects in a scene. We test our method on multiple DVS classification datasets, resulting in an improvement of up to 6.5 % in top1-accuracy.
  arXiv  Detail & Related papers  (2024-01-04T13:49:45Z)
• Leveraging Neural Radiance Fields for Uncertainty-Aware Visual Localization [56.95046107046027]
  We propose to leverage Neural Radiance Fields (NeRF) to generate training samples for scene coordinate regression. Despite NeRF's efficiency in rendering, many of the rendered data are polluted by artifacts or only contain minimal information gain.
  arXiv  Detail & Related papers  (2023-10-10T20:11:13Z)
• Local Magnification for Data and Feature Augmentation [53.04028225837681]
  We propose an easy-to-implement and model-free data augmentation method called Local Magnification (LOMA) LOMA generates additional training data by randomly magnifying a local area of the image. Experiments show that our proposed LOMA, though straightforward, can be combined with standard data augmentation to significantly improve the performance on image classification and object detection.
  arXiv  Detail & Related papers  (2022-11-15T02:51:59Z)
• Exploring the Effects of Data Augmentation for Drivable Area Segmentation [0.0]
  We focus on investigating the benefits of data augmentation by analyzing pre-existing image datasets. Our results show that the performance and robustness of existing state of the art (or SOTA) models can be increased dramatically.
  arXiv  Detail & Related papers  (2022-08-06T03:39:37Z)
• Towards Model Generalization for Monocular 3D Object Detection [57.25828870799331]
  We present an effective unified camera-generalized paradigm (CGP) for Mono3D object detection. We also propose the 2D-3D geometry-consistent object scaling strategy (GCOS) to bridge the gap via an instance-level augment. Our method called DGMono3D achieves remarkable performance on all evaluated datasets and surpasses the SoTA unsupervised domain adaptation scheme.
  arXiv  Detail & Related papers  (2022-05-23T23:05:07Z)
• LENS: Localization enhanced by NeRF synthesis [3.4386226615580107]
  We demonstrate improvement of camera pose regression thanks to an additional synthetic dataset rendered by the NeRF class of algorithm. We further improved localization accuracy of pose regressors using synthesized realistic and geometry consistent images as data augmentation during training.
  arXiv  Detail & Related papers  (2021-10-13T08:15:08Z)
• KeepAugment: A Simple Information-Preserving Data Augmentation Approach [42.164438736772134]
  We propose a simple yet highly effective approach, dubbed emphKeepAugment, to increase augmented images fidelity. The idea is first to use the saliency map to detect important regions on the original images and then preserve these informative regions during augmentation. Empirically, we demonstrate our method significantly improves on a number of prior art data augmentation schemes.
  arXiv  Detail & Related papers  (2020-11-23T22:43:04Z)
• Auto-Rectify Network for Unsupervised Indoor Depth Estimation [119.82412041164372]
  We establish that the complex ego-motions exhibited in handheld settings are a critical obstacle for learning depth. We propose a data pre-processing method that rectifies training images by removing their relative rotations for effective learning. Our results outperform the previous unsupervised SOTA method by a large margin on the challenging NYUv2 dataset.
  arXiv  Detail & Related papers  (2020-06-04T08:59:17Z)

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.