A Little Fog for a Large Turn

• URL: http://arxiv.org/abs/2001.05873v1
• Date: Thu, 16 Jan 2020 15:09:48 GMT
• Title: A Little Fog for a Large Turn
• Authors: Harshitha Machiraju, Vineeth N Balasubramanian
• Abstract summary: We look at the field of Autonomous navigation wherein adverse weather conditions such as fog have a drastic effect on the predictions of these systems. These weather conditions are capable of acting like natural adversaries that can help in testing models. Our work also presents a more natural and general definition of Adversarial perturbations based on Perceptual Similarity.
• Score: 26.556198529742122
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Small, carefully crafted perturbations called adversarial perturbations can easily fool neural networks. However, these perturbations are largely additive and not naturally found. We turn our attention to the field of Autonomous navigation wherein adverse weather conditions such as fog have a drastic effect on the predictions of these systems. These weather conditions are capable of acting like natural adversaries that can help in testing models. To this end, we introduce a general notion of adversarial perturbations, which can be created using generative models and provide a methodology inspired by Cycle-Consistent Generative Adversarial Networks to generate adversarial weather conditions for a given image. Our formulation and results show that these images provide a suitable testbed for steering models used in Autonomous navigation models. Our work also presents a more natural and general definition of Adversarial perturbations based on Perceptual Similarity.

Related papers

• PostCast: Generalizable Postprocessing for Precipitation Nowcasting via Unsupervised Blurriness Modeling [85.56969895866243]
  We propose an unsupervised postprocessing method to eliminate the blurriness without the requirement of training with the pairs of blurry predictions and corresponding ground truth. A zero-shot blur kernel estimation mechanism and an auto-scale denoise guidance strategy are introduced to adapt the unconditional correlations to any blurriness modes.
  arXiv  Detail & Related papers  (2024-10-08T08:38:23Z)
• Precipitation Nowcasting Using Physics Informed Discriminator Generative Models [9.497627628556875]
  State-of-the-art models, including PySTEPS, encounter difficulties in accurately forecasting extreme weather events because of their unpredictable distribution patterns. We design a physics-informed neural network to perform precipitation nowcasting using the precipitation and meteorological data from the Royal Netherlands Meteorological Institute. Our findings demonstrate that the PID-GAN model outperforms numerical and SOTA deep generative models in terms of precipitation nowcasting downstream metrics.
  arXiv  Detail & Related papers  (2024-06-14T15:12:53Z)
• Extreme Miscalibration and the Illusion of Adversarial Robustness [66.29268991629085]
  Adversarial Training is often used to increase model robustness. We show that this observed gain in robustness is an illusion of robustness (IOR) We urge the NLP community to incorporate test-time temperature scaling into their robustness evaluations.
  arXiv  Detail & Related papers  (2024-02-27T13:49:12Z)
• Breaking Free: How to Hack Safety Guardrails in Black-Box Diffusion Models! [52.0855711767075]
  EvoSeed is an evolutionary strategy-based algorithmic framework for generating photo-realistic natural adversarial samples. We employ CMA-ES to optimize the search for an initial seed vector, which, when processed by the Conditional Diffusion Model, results in the natural adversarial sample misclassified by the Model. Experiments show that generated adversarial images are of high image quality, raising concerns about generating harmful content bypassing safety classifiers.
  arXiv  Detail & Related papers  (2024-02-07T09:39:29Z)
• DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting [20.657502066923023]
  Precipitation nowcasting is an important task to predict the radar echoes sequences based on current observations, which can serve both meteorological science and smart city applications. Previous studies address the problem either from the perspectives of deterministic modeling or probabilistic modeling. We propose to decompose and model the chaotic evolutionary precipitation systems from the perspective of global deterministic motion and local variations with residual mechanism.
  arXiv  Detail & Related papers  (2023-12-11T11:26:32Z)
• Learning Robust Precipitation Forecaster by Temporal Frame Interpolation [65.5045412005064]
  We develop a robust precipitation forecasting model that demonstrates resilience against spatial-temporal discrepancies. Our approach has led to significant improvements in forecasting precision, culminating in our model securing textit1st place in the transfer learning leaderboard of the textitWeather4cast'23 competition.
  arXiv  Detail & Related papers  (2023-11-30T08:22:08Z)
• TPSeNCE: Towards Artifact-Free Realistic Rain Generation for Deraining and Object Detection in Rain [23.050711662981655]
  We propose an unpaired image-to-image translation framework for generating realistic rainy images. We first introduce a Triangular Probability Similarity constraint to guide the generated images toward clear and rainy images in the discriminator manifold. Experiments demonstrate realistic rain generation with minimal artifacts and distortions, which benefits image deraining and object detection in rain.
  arXiv  Detail & Related papers  (2023-11-01T17:08:26Z)
• F$^2$AT: Feature-Focusing Adversarial Training via Disentanglement of Natural and Perturbed Patterns [74.03108122774098]
  Deep neural networks (DNNs) are vulnerable to adversarial examples crafted by well-designed perturbations. This could lead to disastrous results on critical applications such as self-driving cars, surveillance security, and medical diagnosis. We propose a Feature-Focusing Adversarial Training (F$2$AT) which enforces the model to focus on the core features from natural patterns.
  arXiv  Detail & Related papers  (2023-10-23T04:31:42Z)
• Generating Clear Images From Images With Distortions Caused by Adverse Weather Using Generative Adversarial Networks [0.0]
  We presented a method for improving computer vision tasks on images affected by adverse weather conditions, including distortions caused by adherent raindrops. We trained an appropriate generative adversarial network and showed that it was effective at removing the effect of the distortions.
  arXiv  Detail & Related papers  (2022-11-01T05:02:44Z)
• fakeWeather: Adversarial Attacks for Deep Neural Networks Emulating Weather Conditions on the Camera Lens of Autonomous Systems [12.118084418840152]
  We emulate the effects of natural weather conditions to introduce plausible perturbations that mislead Deep Neural Networks (DNNs) By observing the effects of such atmospheric perturbations on the camera lenses, we model the patterns to create different masks that fake the effects of rain, snow, and hail. We test our proposed fakeWeather attacks on multiple Convolutional Neural Network and Capsule Network models, and report noticeable accuracy drops in the presence of such adversarial perturbations.
  arXiv  Detail & Related papers  (2022-05-27T07:49:31Z)
• Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of Adverse Weather Conditions for 3D Object Detection [60.89616629421904]
  Lidar-based object detectors are critical parts of the 3D perception pipeline in autonomous navigation systems such as self-driving cars. They are sensitive to adverse weather conditions such as rain, snow and fog due to reduced signal-to-noise ratio (SNR) and signal-to-background ratio (SBR)
  arXiv  Detail & Related papers  (2021-07-14T21:10:47Z)

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.