Corpus ID: 236428518

Learning to Adversarially Blur Visual Object Tracking

@article{Guo2021LearningTA,
  title={Learning to Adversarially Blur Visual Object Tracking},
  author={Qing Guo and Ziyi Cheng and Felix Juefei-Xu and Lei Ma and Xiaofei Xie and Yang Liu and Jianjun Zhao},
  journal={ArXiv},
  year={2021},
  volume={abs/2107.12085}
}
Motion blur caused by the moving of the object or camera during the exposure can be a key challenge for visual object tracking, affecting tracking accuracy significantly. In this work, we explore the robustness of visual object trackers against motion blur from a new angle, i.e., adversarial blur attack (ABA). Our main objective is to online transfer input frames to their natural motion-blurred counterparts while misleading the state-of-the-art trackers during the tracking process. To this end… Expand

References

SHOWING 1-10 OF 50 REFERENCES
One-Shot Adversarial Attacks on Visual Tracking With Dual Attention
TLDR
This paper proposes a novel one-shot adversarial attack method to generate adversarial examples for free-model single object tracking, where merely adding slight perturbations on the target patch in the initial frame causes state-of-the-art trackers to lose the target in subsequent frames. Expand
Physical Adversarial Textures That Fool Visual Object Tracking
  • R. Wiyatno, Anqi Xu
  • Computer Science, Engineering
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
TLDR
While the Expectation Over Transformation (EOT) algorithm is used to generate physical adversaries that fool tracking models when imaged under diverse conditions, the impacts of different scene variables are compared to find practical attack setups with high resulting adversarial strength and convergence speed. Expand
SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation
TLDR
The positive samples generation network (PSGN) is introduced to sampling massive diverse training data through traversing over the constructed target object manifold and generated diverse target object images can enrich the training dataset and enhance the robustness of visual trackers. Expand
Cooling-Shrinking Attack: Blinding the Tracker With Imperceptible Noises
TLDR
A cooling-shrinking attack method is proposed to deceive state-of-the-art SiameseRPN-based trackers using a carefully designed adversarial loss, which can simultaneously cool hot regions where the target exists on the heatmaps and force the predicted bounding box to shrink, making the tracked target invisible to trackers. Expand
Exploring the Effects of Blur and Deblurring to Visual Object Tracking
TLDR
It is found that light motion blur may improve the accuracy of many trackers, but heavy blur usually hurts the tracking performance, and a new general GAN-based scheme is proposed to improve a tracker’s robustness to motion blur. Expand
Learning Dynamic Siamese Network for Visual Object Tracking
TLDR
This paper proposes dynamic Siamese network, via a fast transformation learning model that enables effective online learning of target appearance variation and background suppression from previous frames, and presents elementwise multi-layer fusion to adaptively integrate the network outputs using multi-level deep features. Expand
Motion Deblurring in the Wild
TLDR
A deep learning approach to remove motion blur from a single image captured in the wild, i.e., in an uncontrolled setting, is proposed and both a novel convolutional neural network architecture and a dataset for blurry images with ground truth are designed. Expand
Fully-Convolutional Siamese Networks for Object Tracking
TLDR
A basic tracking algorithm is equipped with a novel fully-convolutional Siamese network trained end-to-end on the ILSVRC15 dataset for object detection in video and achieves state-of-the-art performance in multiple benchmarks. Expand
Triplet Loss in Siamese Network for Object Tracking
TLDR
A novel triplet loss is proposed to extract expressive deep feature for object tracking by adding it into Siamese network framework instead of pairwise loss for training. Expand
Probabilistic Regression for Visual Tracking
TLDR
This work proposes a probabilistic regression formulation and applies it to tracking, which is capable of modeling label noise stemming from inaccurate annotations and ambiguities in the task and substantially improves the performance. Expand
...
1
2
3
4
5
...