A Little Fog for a Large Turn

Machiraju, Harshitha and Balasubramanian, Vineeth N (2020) A Little Fog for a Large Turn. In: Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020, 1 March 2020 - 5 March 2020.

Full text not available from this repository. (Request a copy)

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.

[error in script]

IITH Creators: