Real-Time MDNet

By Ilchae Jung, Jeany Son, Mooyeol Baek, Bohyung Han. European Conference on Computer Vision, 2018

296 citations recorded by the source corpus.

We present a fast and accurate visual tracking algorithm based on the multi-domain convolutional neural network (MDNet). The proposed approach accelerates feature extraction procedure and learns more discriminative models for instance classification; it enhances representation quality of target and background by maintaining a high resolution feature map with a large receptive field per activation. We also introduce a novel loss term to differentiate foreground instances across multiple domains and learn a more discriminative embedding of target objects with similar semantics. The proposed techniques are integrated into the pipeline of a well known CNN-based visual tracking algorithm, MDNet. We accomplish approximately 25 times speed-up with almost identical accuracy compared to MDNet. Our algorithm is evaluated in multiple popular tracking benchmark datasets including OTB2015, UAV123, and TempleColor, and outperforms the state-of-the-art real-time tracking methods consistently even without dataset-specific parameter tuning.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/50003685fe0d72bd77eb675029da922f55b423bc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark (2021, methodology): “We also find that Siamese network based trackers usually achieve better results than other trackers like multi-domain based trackers [26, 44, 45], regression based trackers [21], and correlation filter based trackers [1,8,22].”
Ocean: Object-aware Anchor-free Tracking (2020, methodology): “In visual tracking, there are also several approaches [15,41] considering the correspondence between visual features and candidate bounding boxes.”
Deep Learning for Visual Tracking: A Comprehensive Survey (2019, methodology): “To achieve the goal of learning generic representations for target modeling and constructing a more robust target models, the main contributions of methods are classified into: i) offline training of CNNs on large-scale datasets for visual tracking [63], [68], [80], [89], [97], [100], [101], [104], ”
The Seventh Visual Object Tracking VOT2019 Challenge Results (2019, methodology): “For the veriﬁer RT-MDNet network [42] is used as backbone and is pre-trained on ILSVRC VID dataset.”
Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework (2022, unknown): “SiamFC [1] RT-MDNet [21] ECO [8] Ocean [50] ATOM [7] DiMP50 [2] STMTrack [15] TransT [5] STARK [47] OSTrack -246 OSTrack -384”
Learning Discriminative Model Prediction for Tracking (2019, methodology): “We therefore only show the final AUC scores of these trackers, as obtained from [9] and [6] respectively.”
Learning Spatio-Temporal Transformer for Visual Tracking (2021, methodology): “Speciﬁcally, previous methods usually consist of multiple components, such as base trackers [9, 50], target veriﬁcation modules [21], and global detectors [40, 19].”
GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild (2018, methodology): “In this work, we consider siamese tracker SiamFC [46] and its variants CFNet [63], DCFNet [75], DSiam [72], SASiam [76], and SiamDW [78]; recurrent tracker MemTracker [80]; meta-learning based tracker MetaTracker [61]; attentive tracker DAT [79]; and other convolutional neural networks based approac”
Unsupervised Deep Tracking (2019, methodology): “The stateof-the-art deep tracking methods [1, 46, 15, 55, 27, 60, 58, 54, 4, 19, 33, 34] typically use pretrained CNN models for feature extraction.”