Distractor-Aware Deep Regression for Visual Tracking

Du, Ming; Ding, Yang; Meng, Xiuyun; Wei, Hua‐Liang; Zhao, Yifan

doi:10.3390/s19020387

Cited by 4 publications

(3 citation statements)

References 116 publications

(245 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, residual learning is employed in order to avoid model degradation, instead of the much more frequently-used method of stacking multiple layers. Other tracking methods learn a similar kind of mapping from samples in the vicinity of the target object using deep regression [6,7], or by estimating and learning depth information [8].…”

Section: Learning Features From Convolutional Layersmentioning

confidence: 99%

A Review of Tracking and Trajectory Prediction Methods for Autonomous Driving

2021

View full text Add to dashboard Cite

This paper provides a literature review of some of the most important concepts, techniques, and methodologies used within autonomous car systems. Specifically, we focus on two aspects extensively explored in the related literature: tracking, i.e., identifying pedestrians, cars or obstacles from images, observations or sensor data, and prediction, i.e., anticipating the future trajectories and motion of other vehicles in order to facilitate navigating through various traffic conditions. Approaches based on deep neural networks and others, especially stochastic techniques, are reported.

show abstract

Section: Learning Features From Convolutional Layersmentioning

confidence: 99%

A Review of Tracking and Trajectory Prediction Methods for Autonomous Driving

2021

View full text Add to dashboard Cite

show abstract

“…Furthermore, residual learning is employed in order to avoid model degradation, instead of the much more frequently-used method of stacking multiple layers. Other tracking methods learn a similar kind of mapping from samples in the vicinity of the target object using deep regression [97], [28], or by estimating and learning depth information [109].…”

Section: Learning Features From Convolutional Layersmentioning

confidence: 99%

A Review of Tracking, Prediction and Decision Making Methods for Autonomous Driving

Leon,

Gavrilescu

2019

Preprint

View full text Add to dashboard Cite

This literature review focuses on three important aspects of an autonomous car system: tracking (assessing the identity of the actors such as cars, pedestrians or obstacles in a sequence of observations), prediction (predicting the future motion of surrounding vehicles in order to navigate through various traffic scenarios) and decision making (analyzing the available actions of the ego car and their consequences to the entire driving context). For tracking and prediction, approaches based on (deep) neural networks and other, especially stochastic techniques, are reported. For decision making, deep reinforcement learning algorithms are presented, together with methods used to explore different alternative actions, such as Monte Carlo Tree Search.

show abstract

“…Convolutional neural networks (CNNs) have shown remarkable achievements in various vision tasks [1][2][3][4][5][6][7][8]. Most of the achievements benefit from the innovative design of network architectures [9][10][11][12][13][14], with applications in a variety of areas including phishing detection (see, e.g., [15]).…”

Section: Introductionmentioning

confidence: 99%

LdsConv: Learned Depthwise Separable Convolutions by Group Pruning

Lin

Ding

Wei

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

Standard convolutional filters usually capture unnecessary overlap of features resulting in a waste of computational cost. In this paper, we aim to solve this problem by proposing a novel Learned Depthwise Separable Convolution (LdsConv) operation that is smart but has a strong capacity for learning. It integrates the pruning technique into the design of convolutional filters, formulated as a generic convolutional unit that can be used as a direct replacement of convolutions without any adjustments of the architecture. To show the effectiveness of the proposed method, experiments are carried out using the state-of-the-art convolutional neural networks (CNNs), including ResNet, DenseNet, SE-ResNet and MobileNet, respectively. The results show that by simply replacing the original convolution with LdsConv in these CNNs, it can achieve a significantly improved accuracy while reducing computational cost. For the case of ResNet50, the FLOPs can be reduced by 40.9%, meanwhile the accuracy on the associated ImageNet increases.

show abstract

Distractor-Aware Deep Regression for Visual Tracking

Cited by 4 publications

References 116 publications

A Review of Tracking and Trajectory Prediction Methods for Autonomous Driving

A Review of Tracking and Trajectory Prediction Methods for Autonomous Driving

A Review of Tracking, Prediction and Decision Making Methods for Autonomous Driving

LdsConv: Learned Depthwise Separable Convolutions by Group Pruning

Contact Info

Product

Resources

About