Corpus ID: 236428518

Learning to Adversarially Blur Visual Object Tracking

  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},
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
AdvBokeh: Learning to Adversarially Defocus Blur
Bokeh effect is a natural shallow depth-of-field phenomenon that blurs the out-of-focus part in photography. In pursuit of aesthetically pleasing photos, people usually regard the bokeh effect as anExpand
ArchRepair: Block-Level Architecture-Oriented Repairing for Deep Neural Networks
  • Hua Qi, Zhijie Wang, +4 authors Jianjun Zhao
  • Computer Science
  • ArXiv
  • 2021
Over the past few years, deep neural networks (DNNs) have achieved tremendous success and have been continuously applied in many application domains. However, during the practical deployment in theExpand
Benchmarking Shadow Removal for Facial Landmark Detection and Beyond
  • Lan Fu, Qing Guo, +4 authors Song Wang
  • Computer Science
  • ArXiv
  • 2021
Facial landmark detection is a very fundamental and significant vision task with many important applications. In practice, the facial landmark detection can be affected by a lot of naturalExpand
Pasadena: Perceptually Aware and Stealthy Adversarial Denoise Attack
This paper proposes the adversarial denoise attack aiming to simultaneously denoise input images while fooling DNNs and identifies a totally new task that stealthily embeds attacks inside image denoising module widely deployed in multimedia devices as an image post-processing operation. Expand
Can You Spot the Chameleon? Adversarially Camouflaging Images from Co-Salient Object Detection
  • Ruijun Gao, Qing Guo, +5 authors Song Wang
  • Computer Science
  • 2020
Co-salient object detection (CoSOD) has recently achieved significant progress and played a key role in retrieval-related tasks. However, it inevitably poses an entirely new safety and securityExpand


One-Shot Adversarial Attacks on Visual Tracking With Dual Attention
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
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
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
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
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
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
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
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
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
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