Adversarial Patch Attacks on Monocular Depth Estimation Networks
- URL: http://arxiv.org/abs/2010.03072v1
- Date: Tue, 6 Oct 2020 22:56:22 GMT
- Title: Adversarial Patch Attacks on Monocular Depth Estimation Networks
- Authors: Koichiro Yamanaka, Ryutaroh Matsumoto, Keita Takahashi, and Toshiaki
Fujii
- Abstract summary: We propose a method of adversarial patch attack on monocular depth estimation.
We generate artificial patterns that can fool the target methods into estimating an incorrect depth for the regions where the patterns are placed.
Our method can be implemented in the real world by physically placing the printed patterns in real scenes.
- Score: 7.089737454146505
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Thanks to the excellent learning capability of deep convolutional neural
networks (CNN), monocular depth estimation using CNNs has achieved great
success in recent years. However, depth estimation from a monocular image alone
is essentially an ill-posed problem, and thus, it seems that this approach
would have inherent vulnerabilities. To reveal this limitation, we propose a
method of adversarial patch attack on monocular depth estimation. More
specifically, we generate artificial patterns (adversarial patches) that can
fool the target methods into estimating an incorrect depth for the regions
where the patterns are placed. Our method can be implemented in the real world
by physically placing the printed patterns in real scenes. We also analyze the
behavior of monocular depth estimation under attacks by visualizing the
activation levels of the intermediate layers and the regions potentially
affected by the adversarial attack.
Related papers
- SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for
Dynamic Scenes [58.89295356901823]
Self-supervised monocular depth estimation has shown impressive results in static scenes.
It relies on the multi-view consistency assumption for training networks, however, that is violated in dynamic object regions.
We introduce an external pretrained monocular depth estimation model for generating single-image depth prior.
Our model can predict sharp and accurate depth maps, even when training from monocular videos of highly-dynamic scenes.
arXiv Detail & Related papers (2022-11-07T16:17:47Z) - Image Masking for Robust Self-Supervised Monocular Depth Estimation [12.435468563991174]
Self-supervised monocular depth estimation is a salient task for 3D scene understanding.
We propose MIMDepth, a method that adapts masked image modeling for self-supervised monocular depth estimation.
arXiv Detail & Related papers (2022-10-05T15:57:53Z) - SelfTune: Metrically Scaled Monocular Depth Estimation through
Self-Supervised Learning [53.78813049373321]
We propose a self-supervised learning method for the pre-trained supervised monocular depth networks to enable metrically scaled depth estimation.
Our approach is useful for various applications such as mobile robot navigation and is applicable to diverse environments.
arXiv Detail & Related papers (2022-03-10T12:28:42Z) - Pseudo Supervised Monocular Depth Estimation with Teacher-Student
Network [90.20878165546361]
We propose a new unsupervised depth estimation method based on pseudo supervision mechanism.
It strategically integrates the advantages of supervised and unsupervised monocular depth estimation.
Our experimental results demonstrate that the proposed method outperforms the state-of-the-art on the KITTI benchmark.
arXiv Detail & Related papers (2021-10-22T01:08:36Z) - Variational Monocular Depth Estimation for Reliability Prediction [12.951621755732544]
Self-supervised learning for monocular depth estimation is widely investigated as an alternative to supervised learning approach.
Previous works have successfully improved the accuracy of depth estimation by modifying the model structure.
In this paper, we theoretically formulate a variational model for the monocular depth estimation to predict the reliability of the estimated depth image.
arXiv Detail & Related papers (2020-11-24T06:23:51Z) - Adaptive confidence thresholding for monocular depth estimation [83.06265443599521]
We propose a new approach to leverage pseudo ground truth depth maps of stereo images generated from self-supervised stereo matching methods.
The confidence map of the pseudo ground truth depth map is estimated to mitigate performance degeneration by inaccurate pseudo depth maps.
Experimental results demonstrate superior performance to state-of-the-art monocular depth estimation methods.
arXiv Detail & Related papers (2020-09-27T13:26:16Z) - Calibrating Self-supervised Monocular Depth Estimation [77.77696851397539]
In the recent years, many methods demonstrated the ability of neural networks to learn depth and pose changes in a sequence of images, using only self-supervision as the training signal.
We show that incorporating prior information about the camera configuration and the environment, we can remove the scale ambiguity and predict depth directly, still using the self-supervised formulation and not relying on any additional sensors.
arXiv Detail & Related papers (2020-09-16T14:35:45Z) - Targeted Adversarial Perturbations for Monocular Depth Prediction [74.61708733460927]
We study the effect of adversarial perturbations on the task of monocular depth prediction.
Specifically, we explore the ability of small, imperceptible additive perturbations to selectively alter the perceived geometry of the scene.
We show that such perturbations can not only globally re-scale the predicted distances from the camera, but also alter the prediction to match a different target scene.
arXiv Detail & Related papers (2020-06-12T19:29:43Z) - Monocular Depth Estimators: Vulnerabilities and Attacks [6.821598757786515]
Recent advancements of neural networks lead to reliable monocular depth estimation.
Deep neural networks are highly vulnerable to adversarial samples for tasks like classification, detection and segmentation.
In this paper, we investigate the annihilation of the most state-of-the-art monocular depth estimation networks against adversarial attacks.
arXiv Detail & Related papers (2020-05-28T21:25:21Z) - Adversarial Attacks on Monocular Depth Estimation [27.657287164064687]
We present the first systematic study of adversarial attacks on monocular depth estimation.
In this paper, we first define a taxonomy of different attack scenarios for depth estimation.
We then adapt several state-of-the-art attack methods for classification on the field of depth estimation.
arXiv Detail & Related papers (2020-03-23T15:04:30Z)
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.