/pdf/convex-analysisnoer-san-nojin-zhan-nituite-5dl2rbmoyr.pdf

Convex Analysisの二,三の進展について

Recent advances in convolutional neural networks

We propose a novel visual tracking algorithm based on the representations from a discriminatively trained Convolutional Neural Network (CNN). Our algorithm pretrains a CNN using a large set of videos with tracking groundtruths to obtain a generic target representation. Our network is composed of shared layers and multiple branches of domain-specific layers, where domains correspond to individual training sequences and each branch is responsible for binary classification to identify target in each domain. We train each domain in the network iteratively to obtain generic target representations in the shared layers. When tracking a target in a new sequence, we construct a new network by combining the shared layers in the pretrained CNN with a new binary classification layer, which is updated online. Online tracking is performed by evaluating the candidate windows randomly sampled around the previous target state. The proposed algorithm illustrates outstanding performance in existing tracking benchmarks.

/pdf/learning-multi-domain-convolutional-neural-networks-for-a7hwbgnxpx.pdf

Learning Multi-domain Convolutional Neural Networks for Visual Tracking

We propose a novel visual tracking algorithm based on the representations from a discriminatively trained Convolutional Neural Network (CNN). Our algorithm pretrains a CNN using a large set of videos with tracking ground-truths to obtain a generic target representation. Our network is composed of shared layers and multiple branches of domain-specific layers, where domains correspond to individual training sequences and each branch is responsible for binary classification to identify the target in each domain. We train the network with respect to each domain iteratively to obtain generic target representations in the shared layers. When tracking a target in a new sequence, we construct a new network by combining the shared layers in the pretrained CNN with a new binary classification layer, which is updated online. Online tracking is performed by evaluating the candidate windows randomly sampled around the previous target state. The proposed algorithm illustrates outstanding performance compared with state-of-the-art methods in existing tracking benchmarks.

Learning Multi-Domain Convolutional Neural Networks for Visual Tracking

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.

/pdf/hierarchical-convolutional-features-for-visual-tracking-2cp99smb5x.pdf

Hierarchical Convolutional Features for Visual Tracking

The l 1 tracker obtains robustness by seeking a sparse representation of the tracking object via l 1 norm minimization. However, the high computational complexity involved in the l 1 tracker may hamper its applications in real-time processing scenarios. Here we propose Real-time Com-pressive Sensing Tracking (RTCST) by exploiting the signal recovery power of Compressive Sensing (CS). Dimensionality reduction and a customized Orthogonal Matching Pursuit (OMP) algorithm are adopted to accelerate the CS tracking. As a result, our algorithm achieves a realtime speed that is up to 5,000 times faster than that of the l 1 tracker. Meanwhile, RTCST still produces competitive (sometimes even superior) tracking accuracy compared to the l 1 tracker. Furthermore, for a stationary camera, a refined tracker is designed by integrating a CS-based background model (CSBM) into tracking. This CSBM-equipped tracker, termed RTCST-B, outperforms most state-of-the-art trackers in terms of both accuracy and robustness. Finally, our experimental results on various video sequences, which are verified by a new metric — Tracking Success Probability (TSP), demonstrate the excellence of the proposed algorithms.

Real-time visual tracking using compressive sensing

Deep neural networks, albeit their great success on feature learning in various computer vision tasks, are usually considered as impractical for online visual tracking, because they require very long training time and a large number of training samples. In this paper, we present an efficient and very robust tracking algorithm using a single convolutional neural network (CNN) for learning effective feature representations of the target object in a purely online manner. Our contributions are multifold. First, we introduce a novel truncated structural loss function that maintains as many training samples as possible and reduces the risk of tracking error accumulation. Second, we enhance the ordinary stochastic gradient descent approach in CNN training with a robust sample selection mechanism. The sampling mechanism randomly generates positive and negative samples from different temporal distributions, which are generated by taking the temporal relations and label noise into account. Finally, a lazy yet effective updating scheme is designed for CNN training. Equipped with this novel updating algorithm, the CNN model is robust to some long-existing difficulties in visual tracking, such as occlusion or incorrect detections, without loss of the effective adaption for significant appearance changes. In the experiment, our CNN tracker outperforms all compared state-of-the-art methods on two recently proposed benchmarks, which in total involve over 60 video sequences. The remarkable performance improvement over the existing trackers illustrates the superiority of the feature representations, which are learned purely online via the proposed deep learning framework.

DeepTrack: Learning Discriminative Feature Representations Online for Robust Visual Tracking

Defining hand-crafted feature representations needs expert knowledge, requires timeconsuming manual adjustments, and besides, it is arguably one of the limiting factors of object tracking. In this paper, we propose a novel solution to automatically relearn the most useful feature representations during the tracking process in order to accurately adapt appearance changes, pose and scale variations while preventing from drift and tracking failures. We employ a candidate pool of multiple Convolutional Neural Networks (CNNs) as a data-driven model of different instances of the target object. Individually, each CNN maintains a specific set of kernels that favourably discriminate object patches from their surrounding background using all available low-level cues. These kernels are updated in an online manner at each frame after being trained with just one instance at the initialization of the corresponding CNN. Given a frame, the most promising CNNs in the pool are selected to evaluate the hypothesises for the target object. The hypothesis with the highest score is assigned as the current detection window and the selected models are retrained using a warm-start back-propagation which optimizes a structural loss function. In addition to the model-free tracker, we introduce a class-specific version of the proposed method that is tailored for tracking of a particular object class such as human faces. Our experiments on a large selection of videos from the recent benchmarks demonstrate that our method outperforms the existing state-of-the-art algorithms and rarely loses the track of the target object.

/pdf/deeptrack-learning-discriminative-feature-representations-by-3b63vdtucb.pdf

DeepTrack: learning discriminative feature representations by convolutional neural networks for visual tracking

We study boosting algorithms from a new perspective. We show that the Lagrange dual problems of l1-norm-regularized AdaBoost, LogitBoost, and soft-margin LPBoost with generalized hinge loss are all entropy maximization problems. By looking at the dual problems of these boosting algorithms, we show that the success of boosting algorithms can be understood in terms of maintaining a better margin distribution by maximizing margins and at the same time controlling the margin variance. We also theoretically prove that approximately, l1-norm-regularized AdaBoost maximizes the average margin, instead of the minimum margin. The duality formulation also enables us to develop column-generation-based optimization algorithms, which are totally corrective. We show that they exhibit almost identical classification results to that of standard stagewise additive boosting algorithms but with much faster convergence rates. Therefore, fewer weak classifiers are needed to build the ensemble using our proposed optimization technique.

On the Dual Formulation of Boosting Algorithms

Deep neural networks, albeit their great success on feature learning in various computer vision tasks, are usually considered as impractical for online visual tracking because they require very long training time and a large number of training samples. In this work, we present an efficient and very robust online tracking algorithm using a single Convolutional Neural Network (CNN) for learning effective feature representations of the target object over time. Our contributions are multifold: First, we introduce a novel truncated structural loss function that maintains as many training samples as possible and reduces the risk of tracking error accumulation, thus drift, by accommodating the uncertainty of the model output. Second, we enhance the ordinary Stochastic Gradient Descent approach in CNN training with a temporal selection mechanism, which generates positive and negative samples within different time periods. Finally, we propose to update the CNN model in a “lazy” style to speed-up the training stage, where the network is updated only when a significant appearance change occurs on the object, without sacrificing tracking accuracy. The CNN tracker outperforms all compared state-of-the-art methods in our extensive evaluations that involve 18 well-known benchmark video sequences.

Hanxi Li

Papers

Real-time visual tracking using compressive sensing

DeepTrack: Learning Discriminative Feature Representations Online for Robust Visual Tracking

DeepTrack: learning discriminative feature representations by convolutional neural networks for visual tracking

On the Dual Formulation of Boosting Algorithms

Robust online visual tracking with a single convolutional neural network