Quadruplet Network With One-Shot Learning for Fast Visual Object Tracking

Dong, Xingping; Shen, Jianbing; Wu, Dongming; Guo, Kan; Jin, Xiaogang; Porikli, Fatih

doi:10.1109/tip.2019.2898567

Cited by 164 publications

(41 citation statements)

References 54 publications

(75 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…represent luminance and chrominance respectively. 2 Convert the image to wavelet domainX adv =Xc +ρ using discrete wavelet transform. 3 Remove noisy wavelet coefficients using BayesShrink soft-thresholding.…”

Section: Algorithmic Descriptionmentioning

confidence: 99%

Image Super-Resolution as a Defense Against Adversarial Attacks

Mustafa

Khan

Hayat

et al. 2020

IEEE Trans. on Image Process.

Self Cite

125

View full text Add to dashboard Cite

Convolutional Neural Networks have achieved significant success across multiple computer vision tasks. However, they are vulnerable to carefully crafted, human-imperceptible adversarial noise patterns which constrain their deployment in critical security-sensitive systems. This paper proposes a computationally efficient image enhancement approach that provides a strong defense mechanism to effectively mitigate the effect of such adversarial perturbations. We show that deep image restoration networks learn mapping functions that can bring off-the-manifold adversarial samples onto the natural image manifold, thus restoring classification towards correct classes. A distinguishing feature of our approach is that, in addition to providing robustness against attacks, it simultaneously enhances image quality and retains models performance on clean images. Furthermore, the proposed method does not modify the classifier or requires a separate mechanism to detect adversarial images. The effectiveness of the scheme has been demonstrated through extensive experiments, where it has proven a strong defense in gray-box settings. The proposed scheme is simple and has the following advantages: (1) it does not require any model training or parameter optimization, (2) it complements other existing defense mechanisms, (3) it is agnostic to the attacked model and attack type and (4) it provides superior performance across all popular attack algorithms. Our codes are publicly available at https:// github.com/aamir-mustafa/super-resolution-adversarial-defense.

show abstract

Section: Algorithmic Descriptionmentioning

confidence: 99%

Image Super-Resolution as a Defense Against Adversarial Attacks

Mustafa

Khan

Hayat

et al. 2020

IEEE Trans. on Image Process.

Self Cite

125

View full text Add to dashboard Cite

show abstract

“…Previously, many experts and scholars have studied the trajectory tracking by videos or images with the help of object tracking [55]- [57], [59]- [62], where a CNN structure is used in position tracking based on image data. In view of the temporal dimension of tropical cyclones, the tropical cyclone track prediction is a task of time sequence prediction.…”

Section: Related Workmentioning

confidence: 99%

A Novel Data-Driven Tropical Cyclone Track Prediction Model Based on CNN and GRU With Multi-Dimensional Feature Selection

et al. 2020

View full text Add to dashboard Cite

Strong tropical cyclones have made a drastic effect on human life and natural environment. As large amounts of meteorological data and monitoring data continue to accumulate, traditional methods for predicting tropical cyclone tracks face numerous challenges regarding their prediction efficiency and accuracy. Deep learning methods recently have been proven to be able to learn both spatial and temporal features from a large amount of dataset and be extremely efficient and accurate for forecasting data in complex structures. In this paper, we propose a novel data-driven deep learning model to predict tropical cyclone tracks using the spatial locations and multiple meteorological factors. This model comprises a multidimensional feature selection layer, a CNN layer and a GRU layer. The proposed model was trained using a dataset of real-world tropical cyclones from the years 1945 to 2017. Through the comparison experiments, the results verify that the proposed model outperforms the traditional forecasting methods, including a climatologically aware forecasting technique, the Sanders Barotropic technique and a numerical weather prediction (NWP) model. In addition, the proposed model has better accuracy than some deep learning methods, including RNN, GRU, CNN, AE-RNN, CNN-RNN, and CNN-GRU without the proposed feature selection layer. INDEX TERMS Tropical cyclones tracks prediction, deep learning, feature selection, typhoon.

show abstract

“…Recently, several Siamese network based trackers [36,37,38,39,40,41] have been proposed to address the above problems, which can improve the tracking accuracy while preserving real-time speeds. For example, DSiam [36] proposes a dynamic Siamese network with transformation learning and EAST [37] learns a decision-making strategy in a reinforcement learning framework for adaptive tracking.…”

Section: Related Workmentioning

confidence: 99%

“…Quad [41] proposes a quadruplet network to detect the potential connections of training instances for better representation. In contrast to the above Siamese based methods, we use the Siamese network to select high-quality proposals for computational efficiency and learn a real-time object-adaptive LSTM network to classify these selected proposals.…”

Section: Related Workmentioning

confidence: 99%

Object-adaptive LSTM network for real-time visual tracking with adversarial data augmentation

Yan

Chen

et al. 2020

Neurocomputing

View full text Add to dashboard Cite

In recent years, deep learning based visual tracking methods have obtained great success owing to the powerful feature representation ability of Convolutional Neural Networks (CNNs). Among these methods, classification-based tracking methods exhibit excellent performance while their speeds are heavily limited by the expensive computation for massive proposal feature extraction. In contrast, matching-based tracking methods (such as Siamese networks) possess remarkable speed superiority.However, the absence of online updating renders these methods unadaptable to significant object appearance variations. In this paper, we propose a novel real-time visual tracking method, which adopts an object-adaptive LSTM network to effectively capture the video sequential dependencies and adaptively learn the object appearance variations. For high computational efficiency, we also present a fast proposal selection strategy, which utilizes the matching-based tracking method to pre-estimate dense proposals and selects high-quality ones to feed to the LSTM network for classification. This strategy efficiently filters out some irrelevant proposals and avoids the redundant computation for feature extraction, which enables our method to operate faster than conventional classification-based tracking methods. In addition, to handle the problems of sample inadequacy and class imbalance during online tracking, we adopt a data augmentation technique based on the Generative Adversarial Network (GAN) to facilitate the training of the LSTM network. Extensive experiments on four visual tracking benchmarks demonstrate the state-of-the-art performance of our method in terms of both tracking accuracy and speed, which exhibits great potentials of recurrent structures for visual tracking.

show abstract

Quadruplet Network With One-Shot Learning for Fast Visual Object Tracking

Cited by 164 publications

References 54 publications

Image Super-Resolution as a Defense Against Adversarial Attacks

Image Super-Resolution as a Defense Against Adversarial Attacks

A Novel Data-Driven Tropical Cyclone Track Prediction Model Based on CNN and GRU With Multi-Dimensional Feature Selection

Object-adaptive LSTM network for real-time visual tracking with adversarial data augmentation

Contact Info

Product

Resources

About