Hierarchical Convolutional Features for Visual Tracking
07 Dec 2015-pp 3074-3082
TL;DR: This paper adaptively learn correlation filters on each convolutional layer to encode the target appearance and hierarchically infer the maximum response of each layer to locate targets.
Abstract: Visual object tracking is challenging as target objects often undergo significant appearance changes caused by deformation, abrupt motion, background clutter and occlusion. In this paper, we exploit features extracted from deep convolutional neural networks trained on object recognition datasets to improve tracking accuracy and robustness. The outputs of the last convolutional layers encode the semantic information of targets and such representations are robust to significant appearance variations. However, their spatial resolution is too coarse to precisely localize targets. In contrast, earlier convolutional layers provide more precise localization but are less invariant to appearance changes. We interpret the hierarchies of convolutional layers as a nonlinear counterpart of an image pyramid representation and exploit these multiple levels of abstraction for visual tracking. Specifically, we adaptively learn correlation filters on each convolutional layer to encode the target appearance. We hierarchically infer the maximum response of each layer to locate targets. Extensive experimental results on a largescale benchmark dataset show that the proposed algorithm performs favorably against state-of-the-art methods.
Citations
More filters
08 Oct 2016
TL;DR: A basic tracking algorithm is equipped with a novel fully-convolutional Siamese network trained end-to-end on the ILSVRC15 dataset for object detection in video and achieves state-of-the-art performance in multiple benchmarks.
Abstract: The problem of arbitrary object tracking has traditionally been tackled by learning a model of the object’s appearance exclusively online, using as sole training data the video itself. Despite the success of these methods, their online-only approach inherently limits the richness of the model they can learn. Recently, several attempts have been made to exploit the expressive power of deep convolutional networks. However, when the object to track is not known beforehand, it is necessary to perform Stochastic Gradient Descent online to adapt the weights of the network, severely compromising the speed of the system. In this paper we equip a basic tracking algorithm with a novel fully-convolutional Siamese network trained end-to-end on the ILSVRC15 dataset for object detection in video. Our tracker operates at frame-rates beyond real-time and, despite its extreme simplicity, achieves state-of-the-art performance in multiple benchmarks.
2,936 citations
Cites background or methods from "Hierarchical Convolutional Features..."
...correlation filters) using the network’s internal representation as features [5,6] or perform SGD (stochastic gradient descent) to fine-tune multiple layers of the network [7–9]....
[...]
...[5] and FCNT [8] have achieved strong results, they have been unable to achieve frame-rate operation due to the relatively high dimension of the conv-net representation....
[...]
21 Jul 2017
TL;DR: This work revisit the core DCF formulation and introduces a factorized convolution operator, which drastically reduces the number of parameters in the model, and a compact generative model of the training sample distribution that significantly reduces memory and time complexity, while providing better diversity of samples.
Abstract: In recent years, Discriminative Correlation Filter (DCF) based methods have significantly advanced the state-of-the-art in tracking. However, in the pursuit of ever increasing tracking performance, their characteristic speed and real-time capability have gradually faded. Further, the increasingly complex models, with massive number of trainable parameters, have introduced the risk of severe over-fitting. In this work, we tackle the key causes behind the problems of computational complexity and over-fitting, with the aim of simultaneously improving both speed and performance. We revisit the core DCF formulation and introduce: (i) a factorized convolution operator, which drastically reduces the number of parameters in the model, (ii) a compact generative model of the training sample distribution, that significantly reduces memory and time complexity, while providing better diversity of samples, (iii) a conservative model update strategy with improved robustness and reduced complexity. We perform comprehensive experiments on four benchmarks: VOT2016, UAV123, OTB-2015, and TempleColor. When using expensive deep features, our tracker provides a 20-fold speedup and achieves a 13.0% relative gain in Expected Average Overlap compared to the top ranked method [12] in the VOT2016 challenge. Moreover, our fast variant, using hand-crafted features, operates at 60 Hz on a single CPU, while obtaining 65.0% AUC on OTB-2015.
1,993 citations
Cites background or methods from "Hierarchical Convolutional Features..."
...OTB2015 Dataset: We compare our tracker with 20 stateof-the-art methods: TLD [22], Struck [19], CFLB [16], ACT [13], TGPR [17], KCF [20], DSST [7], SAMF [25], MEEM [38], DAT [33], LCT [28], HCF [27], SRDCF [9], SRDCFad [10], DeepSRDCF [8], Staple [1], MDNet [31], SiameseFC [2], TCNN [30] and C-COT [12]....
[...]
...As mentioned above, the advancement in DCF tracking performance is predominantly attributed to powerful features and sophisticated learning formulations [8, 12, 27]....
[...]
Posted Content•
TL;DR: In this paper, a fully-convolutional Siamese network is trained end-to-end on the ILSVRC15 dataset for object detection in video, which achieves state-of-the-art performance.
Abstract: The problem of arbitrary object tracking has traditionally been tackled by learning a model of the object's appearance exclusively online, using as sole training data the video itself. Despite the success of these methods, their online-only approach inherently limits the richness of the model they can learn. Recently, several attempts have been made to exploit the expressive power of deep convolutional networks. However, when the object to track is not known beforehand, it is necessary to perform Stochastic Gradient Descent online to adapt the weights of the network, severely compromising the speed of the system. In this paper we equip a basic tracking algorithm with a novel fully-convolutional Siamese network trained end-to-end on the ILSVRC15 dataset for object detection in video. Our tracker operates at frame-rates beyond real-time and, despite its extreme simplicity, achieves state-of-the-art performance in multiple benchmarks.
1,613 citations
21 Jul 2017
TL;DR: In this paper, the Correlation Filter learner is interpreted as a differentiable layer in a deep neural network, which enables learning deep features that are tightly coupled to the correlation filter.
Abstract: The Correlation Filter is an algorithm that trains a linear template to discriminate between images and their translations. It is well suited to object tracking because its formulation in the Fourier domain provides a fast solution, enabling the detector to be re-trained once per frame. Previous works that use the Correlation Filter, however, have adopted features that were either manually designed or trained for a different task. This work is the first to overcome this limitation by interpreting the Correlation Filter learner, which has a closed-form solution, as a differentiable layer in a deep neural network. This enables learning deep features that are tightly coupled to the Correlation Filter. Experiments illustrate that our method has the important practical benefit of allowing lightweight architectures to achieve state-of-the-art performance at high framerates.
1,329 citations
TL;DR: Discriminative Correlation Filters have demonstrated excellent performance for visual object tracking and the key to their success is the ability to efficiently exploit available negative data.
Abstract: Discriminative Correlation Filters (DCF) have demonstrated excellent performance for visual object tracking. The key to their success is the ability to efficiently exploit available negative data by including all shifted versions of a training sample. However, the underlying DCF formulation is restricted to single-resolution feature maps, significantly limiting its potential. In this paper, we go beyond the conventional DCF framework and introduce a novel formulation for training continuous convolution filters. We employ an implicit interpolation model to pose the learning problem in the continuous spatial domain. Our proposed formulation enables efficient integration of multi-resolution deep feature maps, leading to superior results on three object tracking benchmarks: OTB-2015 (+5.1% in mean OP), Temple-Color (+4.6% in mean OP), and VOT2015 (20% relative reduction in failure rate). Additionally, our approach is capable of sub-pixel localization, crucial for the task of accurate feature point tracking. We also demonstrate the effectiveness of our learning formulation in extensive feature point tracking experiments. Code and supplementary material are available at this http URL.
1,324 citations
Cites methods from "Hierarchical Convolutional Features..."
...Surprisingly, in the context of tracking, recent DCF-based methods [10,35] have...
[...]
...The DCF-based trackers HCF and Staple obtain AUC scores of 56.6% and 58.4% respectively....
[...]
...[35] employed multiple convolutional layers in a hierarchical ensemble of independent DCF trackers....
[...]
...We validate our Continuous Convolution Operator Tracker (C-COT) in a comprehensive comparison with 20 state-of-the-art methods: ASLA [25], TLD [26], Struck [21], LSHT [22], EDFT [14], DFT [41], CFLB [18], ACT [13], TGPR [19], KCF [24], DSST [9], SAMF [31], MEEM [47], DAT [40], LCT [36], HCF [35], Staple [3] and SRDCF [11]....
[...]
...The HCF tracker, based on hierarchical convolutional features, obtains a mean OP of 65.5%....
[...]
References
More filters
Proceedings Article•
03 Dec 2012TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Abstract: We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overriding in the fully-connected layers we employed a recently-developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.
73,978 citations
Proceedings Article•
01 Jan 2015TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.
49,914 citations
20 Jun 2009
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Abstract: The explosion of image data on the Internet has the potential to foster more sophisticated and robust models and algorithms to index, retrieve, organize and interact with images and multimedia data. But exactly how such data can be harnessed and organized remains a critical problem. We introduce here a new database called “ImageNet”, a large-scale ontology of images built upon the backbone of the WordNet structure. ImageNet aims to populate the majority of the 80,000 synsets of WordNet with an average of 500-1000 clean and full resolution images. This will result in tens of millions of annotated images organized by the semantic hierarchy of WordNet. This paper offers a detailed analysis of ImageNet in its current state: 12 subtrees with 5247 synsets and 3.2 million images in total. We show that ImageNet is much larger in scale and diversity and much more accurate than the current image datasets. Constructing such a large-scale database is a challenging task. We describe the data collection scheme with Amazon Mechanical Turk. Lastly, we illustrate the usefulness of ImageNet through three simple applications in object recognition, image classification and automatic object clustering. We hope that the scale, accuracy, diversity and hierarchical structure of ImageNet can offer unparalleled opportunities to researchers in the computer vision community and beyond.
49,639 citations
20 Jun 2005
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Abstract: We study the question of feature sets for robust visual object recognition; adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient based descriptors, we show experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection. We study the influence of each stage of the computation on performance, concluding that fine-scale gradients, fine orientation binning, relatively coarse spatial binning, and high-quality local contrast normalization in overlapping descriptor blocks are all important for good results. The new approach gives near-perfect separation on the original MIT pedestrian database, so we introduce a more challenging dataset containing over 1800 annotated human images with a large range of pose variations and backgrounds.
31,952 citations
"Hierarchical Convolutional Features..." refers methods in this paper
...The KCF tracker learns a kernelized correlation filter with a Gaussian kernel over HOG features....
[...]
..., HOG [5] or color-attributes [7]) and we construct multiple correlation filters on hierarchical convolutional layers as opposed to only one single filter by existing approaches....
[...]
...The main differences lie in the use of learned CNN features rather than hand-crafted features (e.g., HOG [5] or color-attributes [7]) and we construct multiple correlation filters on hierarchical convolutional layers as opposed to only one single filter by existing approaches....
[...]
23 Jun 2014
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.
Abstract: Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also present experiments that provide insight into what the network learns, revealing a rich hierarchy of image features. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.
21,729 citations