Left-right Discrepancy for Adversarial Attack on Stereo Networks

• URL: http://arxiv.org/abs/2401.07188v1
• Date: Sun, 14 Jan 2024 02:30:38 GMT
• Title: Left-right Discrepancy for Adversarial Attack on Stereo Networks
• Authors: Pengfei Wang, Xiaofei Hui, Beijia Lu, Nimrod Lilith, Jun Liu, Sameer Alam
• Abstract summary: We introduce a novel adversarial attack approach that generates perturbation noise specifically designed to maximize the discrepancy between left and right image features. Experiments demonstrate the superior capability of our method to induce larger prediction errors in stereo neural networks.
• Score: 8.420135490466851
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Stereo matching neural networks often involve a Siamese structure to extract intermediate features from left and right images. The similarity between these intermediate left-right features significantly impacts the accuracy of disparity estimation. In this paper, we introduce a novel adversarial attack approach that generates perturbation noise specifically designed to maximize the discrepancy between left and right image features. Extensive experiments demonstrate the superior capability of our method to induce larger prediction errors in stereo neural networks, e.g. outperforming existing state-of-the-art attack methods by 219% MAE on the KITTI dataset and 85% MAE on the Scene Flow dataset. Additionally, we extend our approach to include a proxy network black-box attack method, eliminating the need for access to stereo neural network. This method leverages an arbitrary network from a different vision task as a proxy to generate adversarial noise, effectively causing the stereo network to produce erroneous predictions. Our findings highlight a notable sensitivity of stereo networks to discrepancies in shallow layer features, offering valuable insights that could guide future research in enhancing the robustness of stereo vision systems.

Related papers

• Stereo Risk: A Continuous Modeling Approach to Stereo Matching [110.22344879336043]
  We introduce Stereo Risk, a new deep-learning approach to solve the classical stereo-matching problem in computer vision. We demonstrate that Stereo Risk enhances stereo-matching performance for deep networks, particularly for disparities with multi-modal probability distributions. A comprehensive analysis demonstrates our method's theoretical soundness and superior performance over the state-of-the-art methods across various benchmark datasets.
  arXiv  Detail & Related papers  (2024-07-03T14:30:47Z)
• StereoVoxelNet: Real-Time Obstacle Detection Based on Occupancy Voxels from a Stereo Camera Using Deep Neural Networks [32.7826524859756]
  Obstacle detection is a safety-critical problem in robot navigation, where stereo matching is a popular vision-based approach. This paper proposes a computationally efficient method that leverages a deep neural network to detect occupancy from stereo images directly. Our approach detects obstacles accurately in the range of 32 meters and achieves better IoU (Intersection over Union) and CD (Chamfer Distance) scores with only 2% of the computation cost of the state-of-the-art stereo model.
  arXiv  Detail & Related papers  (2022-09-18T03:32:38Z)
• Bayesian Learning for Disparity Map Refinement for Semi-Dense Active Stereo Vision [30.330599857204344]
  We propose a new learning strategy to train neural networks to estimate high-quality subpixel disparity maps for semi-dense active stereo vision. We demonstrate that the proposed method outperforms the current state-of-the-art active stereo models.
  arXiv  Detail & Related papers  (2022-09-12T08:33:40Z)
• From Environmental Sound Representation to Robustness of 2D CNN Models Against Adversarial Attacks [82.21746840893658]
  This paper investigates the impact of different standard environmental sound representations (spectrograms) on the recognition performance and adversarial attack robustness of a victim residual convolutional neural network. We show that while the ResNet-18 model trained on DWT spectrograms achieves a high recognition accuracy, attacking this model is relatively more costly for the adversary.
  arXiv  Detail & Related papers  (2022-04-14T15:14:08Z)
• Stereoscopic Universal Perturbations across Different Architectures and Datasets [60.021985610201156]
  We study the effect of adversarial perturbations of images on deep stereo matching networks for the disparity estimation task. We present a method to craft a single set of perturbations that, when added to any stereo image pair in a dataset, can fool a stereo network. Our perturbations can increase D1-error (akin to fooling rate) of state-of-the-art stereo networks from 1% to as much as 87%.
  arXiv  Detail & Related papers  (2021-12-12T02:11:31Z)
• SMD-Nets: Stereo Mixture Density Networks [68.56947049719936]
  We propose Stereo Mixture Density Networks (SMD-Nets), a simple yet effective learning framework compatible with a wide class of 2D and 3D architectures. Specifically, we exploit bimodal mixture densities as output representation and show that this allows for sharp and precise disparity estimates near discontinuities. We carry out comprehensive experiments on a new high-resolution and highly realistic synthetic stereo dataset, consisting of stereo pairs at 8Mpx resolution, as well as on real-world stereo datasets.
  arXiv  Detail & Related papers  (2021-04-08T16:15:46Z)
• Stereopagnosia: Fooling Stereo Networks with Adversarial Perturbations [71.00754846434744]
  We show that imperceptible additive perturbations can significantly alter the disparity map. We show that, when used for adversarial data augmentation, our perturbations result in trained models that are more robust.
  arXiv  Detail & Related papers  (2020-09-21T19:20:09Z)
• Learning Stereo Matchability in Disparity Regression Networks [40.08209864470944]
  This paper proposes a stereo matching network that considers pixel-wise matchability. The proposed deep stereo matchability (DSM) framework can improve the matching result or accelerate the computation while still guaranteeing the quality.
  arXiv  Detail & Related papers  (2020-08-11T15:55:49Z)
• A Lightweight Neural Network for Monocular View Generation with Occlusion Handling [46.74874316127603]
  We present a very lightweight neural network architecture, trained on stereo data pairs, which performs view synthesis from one single image. The work outperforms visually and metric-wise state-of-the-art approaches on the challenging KITTI dataset.
  arXiv  Detail & Related papers  (2020-07-24T15:29:01Z)

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.