Deep Siamese Networks toward Robust Visual Tracking

Fiaz, Mustansar; Mahmood, Arif; Jung, Soon Ki

doi:10.5772/intechopen.86235

Cited by 8 publications

(7 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we briefly present the SNN architecture and explain how it works. SNN (Chicco,Figure 3: Three types of SNNs (a) late merge, (b) intermediate merge, and (c) early merge (Fiaz et al, 2019).…”

Section: Preliminarymentioning

confidence: 99%

“…By receiving two different inputs, the main goal of such networks is to develop similarity knowledge between the two produced outputs. Fiaz et al (2019) categorize SNNs in three groups based on the time of merging the layers: late merge (LM), intermediate merge (IM), and early merge (EM), which are shown in Figure 3. In LM, the output vectors of each network are merged at the last dense layer.…”

Section: Preliminarymentioning

confidence: 99%

See 1 more Smart Citation

Siamese Neural Networks for Detecting Complementary Products

Angelovska¹,

Sheikholeslami²,

Dunn³

et al. 2021

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research W

View full text Add to dashboard Cite

Recommender systems play an important role in e-commerce websites as they improve the customer journey by helping the users find what they want at the right moment. In this paper, we focus on identifying a complementary relationship between the products of an e-commerce company. We propose a content-based recommender system for detecting complementary products, using Siamese Neural Networks (SNN). To this end, we implement and compare two different models: Siamese Convolutional Neural Network (CNN) and Siamese Long Short-Term Memory (LSTM). Moreover, we propose an extension of the SNN approach to handling millions of products in a matter of seconds, and we reduce the training time complexity by half. In the experiments, we show that Siamese LSTM can predict complementary products with an accuracy of ∼ 85% using only the product titles.

show abstract

Section: Preliminarymentioning

confidence: 99%

Section: Preliminarymentioning

confidence: 99%

Siamese Neural Networks for Detecting Complementary Products

Angelovska¹,

Sheikholeslami²,

Dunn³

et al. 2021

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research W

View full text Add to dashboard Cite

show abstract

“…It is inconvenient to cover a comprehensive survey of all trackers in the scope of this work. However, these survey studies [31]- [33] help to learn a detailed overview of the tracking frameworks for interested readers. This section provides short outlines for deep feature based trackers [18], [21], [34]- [36], Siamese based trackers [5], [7], [37]- [39], and attention based trackers [22], [40]- [45].…”

Section: Related Workmentioning

confidence: 99%

Efficient Visual Tracking With Stacked Channel-Spatial Attention Learning

2020

Self Cite

View full text Add to dashboard Cite

Template based learning, particularly Siamese networks, has recently become popular due to balancing accuracy and speed. However, preserving tracker robustness against challenging scenarios with real-time speed is a primary concern for visual object tracking. Siamese trackers confront difficulties handling target appearance changes continually due to less discrimination ability learning between target and background information. This paper presents stacked channel-spatial attention within Siamese networks to improve tracker robustness without sacrificing fast-tracking speed. The proposed channel attention strengthens target-specific channels increasing their weight while reducing the importance of irrelevant channels with lower weights. Spatial attention is focusing on the most informative region of the target feature map. We integrate the proposed channel and spatial attention modules to enhance tracking performance with end-to-end learning. The proposed tracking framework learns what and where to highlight important target information for efficient tracking. Experimental results on widely used OTB100, OTB50, VOT2016, VOT2017/18, TC-128, and UAV123 benchmarks verified the proposed tracker achieved outstanding performance compared with state-of-the-art trackers. INDEX TERMS Deep learning, Siamese architecture, stacked channel-spatial attention, visual object tracking.

show abstract

“…A Siamese network comprises of two parallel Convolutional Neural Networks (CNN) streams that are used to learn the similarity between input images in embedded space and to fuse them to produce an output [ 46 ]. Owing to their inherent characteristics such as accuracy and speed, Siamese networks are popular in the visual tracking community [ 10 , 15 , 16 , 17 , 47 ].…”

Section: Related Workmentioning

confidence: 99%

Improving Object Tracking by Added Noise and Channel Attention

Fiaz

Mahmood

Baek

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

CNN-based trackers, especially those based on Siamese networks, have recently attracted considerable attention because of their relatively good performance and low computational cost. For many Siamese trackers, learning a generic object model from a large-scale dataset is still a challenging task. In the current study, we introduce input noise as regularization in the training data to improve generalization of the learned model. We propose an Input-Regularized Channel Attentional Siamese (IRCA-Siam) tracker which exhibits improved generalization compared to the current state-of-the-art trackers. In particular, we exploit offline learning by introducing additive noise for input data augmentation to mitigate the overfitting problem. We propose feature fusion from noisy and clean input channels which improves the target localization. Channel attention integrated with our framework helps finding more useful target features resulting in further performance improvement. Our proposed IRCA-Siam enhances the discrimination of the tracker/background and improves fault tolerance and generalization. An extensive experimental evaluation on six benchmark datasets including OTB2013, OTB2015, TC128, UAV123, VOT2016 and VOT2017 demonstrate superior performance of the proposed IRCA-Siam tracker compared to the 30 existing state-of-the-art trackers.

show abstract

Deep Siamese Networks toward Robust Visual Tracking

Cited by 8 publications

References 53 publications

Siamese Neural Networks for Detecting Complementary Products

Siamese Neural Networks for Detecting Complementary Products

Efficient Visual Tracking With Stacked Channel-Spatial Attention Learning

Improving Object Tracking by Added Noise and Channel Attention

Contact Info

Product

Resources

About