Search

Learning domain-invariant semantic representations is crucial for achieving domain generalization (DG), where a model is required to perform well on unseen target domains. One critical challenge is that standard training often results in entangled semantic and domain-specific features. Previous works suggest formulating the problem from a causal perspective and solving the entanglement problem by enforcing marginal independence between the causal (i.e.semantic) and non-causal (i.e.domain-specific) features. Despite its simplicity, the basic marginal independent-based idea alone may be insufficient to identify the causal feature. By d-separation, we observe that the causal feature can be further characterized by being independent of the domain conditioned on the object, and we propose the following two strategies as complements for the basic framework. First, the observation implicitly implies that for the same object, the causal feature should not be associated with the non-causal feature, revealing that the common practice of obtaining the two features with a shared base feature extractor and two lightweight prediction heads might be inappropriate. To meet the constraint, we propose a simple early-branching structure, where the causal and non-causal feature obtaining branches share the first few blocks while diverging thereafter, for better structure design; Second, the observation implies that the causal feature remains invariant across different domains for the same object. To this end, we suggest that augmentation should be incorporated into the framework to better characterize the causal feature, and we further suggest an effective random domain sampling scheme to fulfill the task. Theoretical and experimental results show that the two strategies are beneficial for the basic marginal independent-based framework. [ABSTRACT FROM AUTHOR]

Siamese networks are prevalent in visual tracking because of the efficient localization. The networks take both a search patch and a target template as inputs where the target template is usually from the initial frame. Meanwhile, Siamese trackers do not update network parameters online for real-time efficiency. The fixed target template and CNN parameters make Siamese trackers not effective to capture target appearance variations. In this paper, we propose a template updating method via reinforcement learning for Siamese regression trackers. We collect a series of templates and learn to maintain them based on an actor-critic framework. Among this framework, the actor network that is trained by deep reinforcement learning effectively updates the templates based on the tracking result on each frame. Besides the target template, we update the Siamese regression tracker online to adapt to target appearance variations. The experimental results on the standard benchmarks show the effectiveness of both template and network updating. The proposed tracker SiamRTU performs favorably against state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Facilitated by deep neural networks, numerous tracking methods have made significant advances. Existing deep trackers mainly utilize independent frames to model the target appearance, while paying less attention to its temporal coherence. In this paper, we propose a recurrent memory activation network (RMAN) to exploit the untapped temporal coherence of the target appearance for visual tracking. We build the RMAN on top of the long short-term memory network (LSTM) with an additional memory activation layer. Specifically, we first use the LSTM to model the temporal changes of the target appearance. Then we selectively activate the memory blocks via the activation layer to produce a temporally coherent representation. The recurrent memory activation layer enriches the target representations from independent frames and reduces the background interference through temporal consistency. The proposed RMAN is fully differentiable and can be optimized end-to-end. To facilitate network training, we propose a temporal coherence loss together with the original binary classification loss. Extensive experimental results on standard benchmarks demonstrate that our method performs favorably against the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

The advancement of visual tracking has continuously been brought by deep learning models. Typically, supervised learning is employed to train these models with expensive labeled data. In order to reduce the workload of manual annotation and learn to track arbitrary objects, we propose an unsupervised learning method for visual tracking. The motivation of our unsupervised learning is that a robust tracker should be effective in bidirectional tracking. Specifically, the tracker is able to forward localize a target object in successive frames and backtrace to its initial position in the first frame. Based on such a motivation, in the training process, we measure the consistency between forward and backward trajectories to learn a robust tracker from scratch merely using unlabeled videos. We build our framework on a Siamese correlation filter network, and propose a multi-frame validation scheme and a cost-sensitive loss to facilitate unsupervised learning. Without bells and whistles, the proposed unsupervised tracker achieves the baseline accuracy of classic fully supervised trackers while achieving a real-time speed. Furthermore, our unsupervised framework exhibits a potential in leveraging more unlabeled or weakly labeled data to further improve the tracking accuracy. [ABSTRACT FROM AUTHOR]

In this article, we present an end-to-end learning framework for detailed 3D face reconstruction from a single image. Our approach uses a 3DMM-based coarse model and a displacement map in UV-space to represent a 3D face. Unlike previous work addressing the problem, our learning framework does not require supervision of surrogate ground-truth 3D models computed with traditional approaches. Instead, we utilize the input image itself as supervision during learning. In the first stage, we combine a photometric loss and a facial perceptual loss between the input face and the rendered face, to regress a 3DMM-based coarse model. In the second stage, both the input image and the regressed texture of the coarse model are unwrapped into UV-space, and then sent through an image-to-image translation network to predict a displacement map in UV-space. The displacement map and the coarse model are used to render a final detailed face, which again can be compared with the original input image to serve as a photometric loss for the second stage. The advantage of learning displacement map in UV-space is that face alignment can be explicitly done during the unwrapping, thus facial details are easier to learn from large amount of data. Extensive experiments demonstrate the superiority of our method over previous work. [ABSTRACT FROM AUTHOR]

Correlation filters (CF) have received considerable attention in visual tracking because of their computational efficiency. Leveraging deep features via off-the-shelf CNN models (e.g., VGG), CF trackers achieve state-of-the-art performance while consuming a large number of computing resources. This limits deep CF trackers to be deployed to many mobile platforms on which only a single-core CPU is available. In this paper, we propose to jointly compress and transfer off-the-shelf CNN models within a knowledge distillation framework. We formulate a CNN model pretrained from the image classification task as a teacher network, and distill this teacher network into a lightweight student network as the feature extractor to speed up CF trackers. In the distillation process, we propose a fidelity loss to enable the student network to maintain the representation capability of the teacher network. Meanwhile, we design a tracking loss to adapt the objective of the student network from object recognition to visual tracking. The distillation process is performed offline on multiple layers and adaptively updates the student network using a background-aware online learning scheme. The online adaptation stage exploits the background contents to improve the feature discrimination of the student network. Extensive experiments on six standard datasets demonstrate that the lightweight student network accelerates the speed of state-of-the-art deep CF trackers to real-time on a single-core CPU while maintaining almost the same tracking accuracy. [ABSTRACT FROM AUTHOR]

The synthesis conditions of HZSM-5 zeolite, including crystallization temperature, crystallization time and raw material ratio, were investigated by L32 (48) orthogonal test to specifically optimize its performance in dimethyl ether (DME) aromatization for the first time. Based on the total yield of aromatic products, the synthesis conditions of HZSM-5 zeolite with the best DME aromatization properties were obtained by comprehensive analysis and validation experiments. The relationship between the aromatization performance, crystalline structure, pore structure, and acidity of HZSM-5 zeolite were analyzed. The results showed that the HZSM-5 zeolite accompanied by hierarchical structure, an appropriate Brønsted and Lewis acid content and uniform crystal morphology, was successfully synthesized under optimized conditions. Over this unmodified and un-doped catalyst, the conversion of DME approached to 99.3% and the total yield of aromatics reached was 53.5%. [ABSTRACT FROM AUTHOR]

The tracking-by-detection framework receives growing attention through the integration with the convolutional neural networks (CNNs). Existing tracking-by-detection-based methods, however, fail to track objects with severe appearance variations. This is because the traditional convolutional operation is performed on fixed grids, and thus may not be able to find the correct response while the object is changing pose or under varying environmental conditions. In this paper, we propose a deformable convolution layer to enrich the target appearance representations in the tracking-by-detection framework. We aim to capture the target appearance variations via deformable convolution, which adaptively enhances its original features. In addition, we also propose a gated fusion scheme to control how the variations captured by the deformable convolution affect the original appearance. The enriched feature representation through deformable convolution facilitates the discrimination of the CNN classifier on the target object and background. The extensive experiments on the standard benchmarks show that the proposed tracker performs favorably against the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

We address the problem of restoring a high-resolution face image from a blurry low-resolution input. This problem is difficult as super-resolution and deblurring need to be tackled simultaneously. Moreover, existing algorithms cannot handle face images well as low-resolution face images do not have much texture which is especially critical for deblurring. In this paper, we propose an effective algorithm by utilizing the domain-specific knowledge of human faces to recover high-quality faces. We first propose a facial component guided deep Convolutional Neural Network (CNN) to restore a coarse face image, which is denoted as the base image where the facial component is automatically generated from the input face image. However, the CNN based method cannot handle image details well. We further develop a novel exemplar-based detail enhancement algorithm via facial component matching. Extensive experiments show that the proposed method outperforms the state-of-the-art algorithms both quantitatively and qualitatively. [ABSTRACT FROM AUTHOR]

A sunscreen nanomaterial SiO2-KH550/TiO2 was prepared by using rutile TiO2 as carrier and KH550 as coupling agent by inorganic coating and organic grafting. Its hydrophilic, lipophilic and photocatalytic properties were investigated. The results showed that SiO2-IKH550/TiO2 had good lipophilicity and could be well dispersed in the oil phase with good stability. After 6 h photodegradation, the degradation rate of meth¬ylene blue was only 17%, and the photocatalytic activity of TiO2 was obviously reduced. The material could solve the problem that TiO2 was easy to separate and settle in the oil phase system sunscreen cosmetics, and avoided the damage of epidermal cells caused by the photocatalytic activity of TiO2 during the use of the product. [ABSTRACT FROM AUTHOR]

Let $$G=(V_G, E_G)$$ be a connected graph. The degree distance of $$G$$ is defined as $$D'(G)= \sum _{\{u,v\} \subseteq V_G}(d_G(v)+d_G(v))d_G(u,v)$$ , where $$d_G(v)$$ is the degree of vertex $$v, d_G(u, v)$$ denotes the distance between $$u$$ and $$v$$ in $$G$$ . This parameter was introduced, independently, by Dobrynin and Kochetova and by Gutman as a weighted version of the Wiener index. Feng et al. (Graphs Comb 29(3):449-462, ) characterized $$n$$ -vertex unicyclic graphs with given matching number having the minimal degree distance. As a continuance of it, in this paper the $$n$$ -vertex unicyclic graphs of given matching number with the second and third minimal degree distance are identified respectively. [ABSTRACT FROM AUTHOR]

We present a new efficient edge-preserving filter—“tree filter”—to achieve strong image smoothing. The proposed filter can smooth out high-contrast details while preserving major edges, which is not achievable for bilateral-filter-like techniques. Tree filter is a weighted-average filter, whose kernel is derived by viewing pixel affinity in a probabilistic framework simultaneously considering pixel spatial distance, color/intensity difference, as well as connectedness. Pixel connectedness is acquired by treating pixels as nodes in a minimum spanning tree (MST) extracted from the image. The fact that an MST makes all image pixels connected through the tree endues the filter with the power to smooth out high-contrast, fine-scale details while preserving major image structures, since pixels in small isolated region will be closely connected to surrounding majority pixels through the tree, while pixels inside large homogeneous region will be automatically dragged away from pixels outside the region. The tree filter can be separated into two other filters, both of which turn out to have fast algorithms. We also propose an efficient linear time MST extraction algorithm to further improve the whole filtering speed. The algorithms give tree filter a great advantage in low computational complexity (linear to number of image pixels) and fast speed: it can process a 1-megapixel 8-bit image at \sim0.25~s on an Intel 3.4 GHz Core i7 CPU (including the construction of MST). The proposed tree filter is demonstrated on a variety of applications. [ABSTRACT FROM AUTHOR]

The immobilized metal complexes with the Schiff's base of salen have shown high catalytic activity in oxidation of alkenes, cycloalkenes, and alcohols as compared with their unsupported analogs. Due to the heterogeneous nature of such catalysts, their separation and recycling is rather simple. [ABSTRACT FROM AUTHOR]

Pulsed-radio frequency glow discharge optical emission spectrometry (Pulsed-RF-GDOES) has exhibited great potential for high resolution (HR) depth profiling. In this paper, the measured GDOES depth profile of 60 × Mo (3 nm)/B4C (0.3 nm)/Si (3.7 nm) was quantified by employing the newly extended Mixing-Roughness-Information depth (MRI) model. We evaluated the influences of the thickness and sputtering rate on the depth profile of very thin layers. We demonstrated that a method using the full width at half maximum (FWHM) value of the measured time-concentration profile for determining the sputtering rate and the corresponding thickness was not reliable if preferential sputtering took place upon depth profiling. [ABSTRACT FROM AUTHOR]