FEAR: Fast, Efficient, Accurate and Robust Visual Tracker

Borsuk, Vasyl; Vei, Roman; Kupyn, Orest; Martyniuk, Tetiana; Krashenyi, Igor; Matas, Jiřı́

doi:10.48550/arxiv.2112.07957

Cited by 2 publications

(2 citation statements)

References 51 publications

(141 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Table 8, there are gaps between transformer based models and our ResNet-based model (CLNet*-BAN), since former ones have stronger backbone. Besides, we also show the results of several efficient trackers: E.T.Track [91], LightTrack [92], and FEAR-L [93], which have real-time speeds on the edge-platforms. In future work, we will try to incorporate our CLNet into these recent models with more efficient backbones, to explore a more generalized and practical solution.…”

Section: More Discussionmentioning

confidence: 99%

Adaptive Siamese Tracking with a Compact Latent Network

Dong

Shen

Porikli

et al. 2022

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

In this paper, we provide an intuitive viewing to simplify the Siamese-based trackers by converting the tracking task to a classification. Under this viewing, we perform an in-depth analysis for them through visual simulations and real tracking examples, and find that the failure cases in some challenging situations can be regarded as the issue of missing decisive samples in offline training. Since the samples in the initial (first) frame contain rich sequence-specific information, we can regard them as the decisive samples to represent the whole sequence. To quickly adapt the base model to new scenes, a compact latent network is presented via fully using these decisive samples. Specifically, we present a statistics-based compact latent feature for fast adjustment by efficiently extracting the sequence-specific information. Furthermore, a new diverse sample mining strategy is designed for training to further improve the discrimination ability of the proposed compact latent network. Finally, a conditional updating strategy is proposed to efficiently update the basic models to handle scene variation during the tracking phase. To evaluate the generalization ability and effectiveness and of our method, we apply it to adjust three classical Siamese-based trackers, namely SiamRPN++, SiamFC, and SiamBAN. Extensive experimental results on six recent datasets demonstrate that all three adjusted trackers obtain the superior performance in terms of the accuracy, while having high running speed.

show abstract

Section: More Discussionmentioning

confidence: 99%

Adaptive Siamese Tracking with a Compact Latent Network

Dong

Shen

Porikli

et al. 2022

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

show abstract

“…In [36], they suggested adaptively employing the level set segmentation and bounding box regression techniques to achieve a tight enclosing box, and designing a CNN to determine if the target is occluded. Recent attempts [37][38][39][40][41] have been made to realize higher performance of object tracking by using new schemes.…”

Section: Deep Visual Trackingmentioning

confidence: 99%

Robust visual tracking using very deep generative model

AlBasiouny

Attia²,

Abdelmunim³

et al. 2023

J Big Data

View full text Add to dashboard Cite

Deep learning algorithms provide visual tracking robustness at an unprecedented level, but realizing an acceptable performance is still challenging because of the natural continuous changes in the features of foreground and background objects over videos. One of the factors that most affects the robustness of tracking algorithms is the choice of network architecture parameters, especially the depth. A robust visual tracking model using a very deep generator (RTDG) was proposed in this study. We constructed our model on an ordinary convolutional neural network (CNN), which consists of feature extraction and binary classifier networks. We integrated a generative adversarial network (GAN) into the CNN to enhance the tracking results through an adversarial learning process performed during the training phase. We used the discriminator as a classifier and the generator as a store that produces unlabeled feature-level data with different appearances by applying masks to the extracted features. In this study, we investigated the role of increasing the number of fully connected (FC) layers in adversarial generative networks and their impact on robustness. We used a very deep FC network with 22 layers as a high-performance generator for the first time. This generator is used via adversarial learning to augment the positive samples to reduce the gap between the hungry deep learning algorithm and the available training data to achieve robust visual tracking. The experiments showed that the proposed framework performed well against state-of-the-art trackers on OTB-100, VOT2019, LaSOT and UAVDT benchmark datasets.

show abstract

FEAR: Fast, Efficient, Accurate and Robust Visual Tracker

Cited by 2 publications

References 51 publications

Adaptive Siamese Tracking with a Compact Latent Network

Adaptive Siamese Tracking with a Compact Latent Network

Robust visual tracking using very deep generative model

Contact Info

Product

Resources

About