Weakly supervised image segmentation trained with image-level labels usually suffers from inaccurate coverage of object areas during the generation of the pseudo groundtruth. This is because the object activation maps are trained with the classification objective and lack the ability to generalize. To improve the generality of the object activation maps, we propose a region prototypical network (RPNet) to explore the cross-image object diversity of the training set. Similar object parts across images are identified via region feature comparison. Object confidence is propagated between regions to discover new object areas while background regions are suppressed. Experiments show that the proposed method generates more complete and accurate pseudo object masks while achieving state-of-the-art performance on PASCAL VOC 2012 and MS COCO. In addition, we investigate the robustness of the proposed method on reduced training sets. The code is available athttps://github.com/liuweide01/RPNet-Weakly-Supervised-Segmentation.

In this work, we propose a motion-guided cascaded refinement network for video object segmentation. By assuming the foreground objects show different motion patterns from the background, for each video frame we apply an active contour model on optical flow to coarsely segment the foreground. The proposed Cascaded Refinement Network (CRN) then takes as guidance the coarse segmentation to generate an accurate segmentation in full resolution. In this way, the motion information and the deep CNNs can complement each other well to accurately segment the foreground objects from video frames. To deal with multi-instance cases, we extend our method with a spatial-temporal instance embedding model that further segments the foreground regions into instances and propagates instance labels. We further introduce a single-channel residual attention module in CRN to incorporate the coarse segmentation map as attention, which makes the network effective and efficient in both training and testing. We perform experiments on popular benchmarks and the results show that our method achieves state-of-the-art performance with high time efficiency.

Impedance-source networks refer to a series of converters to achieve a high voltage gain between source and load. Magnetically coupled impedance-source networks were proposed to obtain a higher voltage gain with less shoot-through time compared with early-proposed topologies without magnetically coupled inductors. In this paper, a new topology, named Π-source impedance network, is proposed and analyzed to improve the performance on smaller magnetic core size, wider load range and less circulating current in comparison with the conventional magnetic coupled impedance-source topologies: Y-source and Δ-source. Finally, representative simulation and experimental results are carried out to verify the validity and effectiveness of the proposed Π-source impedance network.

LCL-filtered three-level inverters have been widely used in PV applications because of their high efficiency, high power density, and low cost. In practice, the inverter-side current feedback (ICF) control has dominated the PV market due to its low-cost property. However, the grid-side current becomes more sensitive to the grid distortion owing to its indirect regulation in an ICF controlled system. To address this issue, this paper proposes a new control structure to improve the power factor and eliminate the low-order harmonics of the grid-side current simultaneously. By combining the feedforward and proportional feedback of the capacitor current, this method can effectively eliminate the reactive power induced by the capacitor of an LCL-filter. In addition, the low-order harmonics can also be eliminated if the capacitor current is sent back to the resonant controller. Effectiveness of the proposed method has finally been verified with a 5kW LCL-filtered three-phase T-type PV inverter.

Deep CNNs have achieved superior performance in many tasks of computer vision and image understanding. However, it is still difficult to effectively apply deep CNNs to video object segmentation(VOS) since treating video frames as separate and static will lose the information hidden in motion. To tackle this problem, we propose a Motion-guided Cascaded Refinement Network for VOS. By assuming the object motion is normally different from the background motion, for a video frame we first apply an active contour model on optical flow to coarsely segment objects of interest. Then, the proposed Cascaded Refinement Network(CRN) takes the coarse segmentation as guidance to generate an accurate segmentation of full resolution. In this way, the motion information and the deep CNNs can well complement each other to accurately segment objects from video frames. Furthermore, in CRN we introduce a Single-channel Residual Attention Module to incorporate the coarse segmentation map as attention, making our network effective and efficient in both training and testing. We perform experiments on the popular benchmarks and the results show that our method achieves state-of-the-art performance at a much faster speed.

It is desirable to train convolutional networks (CNNs) to run more efficiently during inference. In many cases however, the computational budget that the system has for inference cannot be known beforehand during training, or the inference budget is dependent on the changing real-time resource availability. Thus, it is inadequate to train just inference-efficient CNNs, whose inference costs are not adjustable and cannot adapt to varied inference budgets. We propose a novel approach for cost-adjustable inference in CNNs - Stochastic Downsampling Point (SDPoint). During training, SDPoint applies feature map downsampling to a random point in the layer hierarchy, with a random downsampling ratio. The different stochastic downsampling configurations known as SDPoint instances (of the same model) have computational costs different from each other, while being trained to minimize the same prediction loss. Sharing network parameters across different instances provides significant regularization boost. During inference, one may handpick a SDPoint instance that best fits the inference budget. The effectiveness of SDPoint, as both a cost-adjustable inference approach and a regularizer, is validated through extensive experiments on image classification.

Typical person re-identification (ReID) methods usually describe each pedestrian with a single feature vector and match them in a task-specific metric space. However, the methods based on a single feature vector are not sufficient enough to overcome visual ambiguity, which frequently occurs in real scenario. In this paper, we propose a novel end-to-end trainable framework, called Dual ATtention Matching network (DuATM), to learn context-aware feature sequences and perform attentive sequence comparison simultaneously. The core component of our DuATM framework is a dual attention mechanism, in which both intrasequence and inter-sequence attention strategies are used for feature refinement and feature-pair alignment, respectively. Thus, detailed visual cues contained in the intermediate feature sequences can be automatically exploited and properly compared. We train the proposed DuATM network as a siamese network via a triplet loss assisted with a decorrelation loss and a cross-entropy loss. We conduct extensive experiments on both image and video based ReID benchmark datasets. Experimental results demonstrate the significant advantages of our approach compared to the state-of-the-art methods.

Given a collection of event-related documents, event ranking generates a list of ranked events based on the input query. Ranking news events, which takes event related news documents for the generation of ranked events, is both an essential research issue and important component for many security oriented applications, such as public event monitoring, retrieval, detection and mining. Previous related work solely relies on queries of event relevant aspects, and user relevant aspects of queries that are critical for security applications are totally ignored. In this paper, we deal with the problem of news ranking by incorporating user relevant information into the input query, from the cluster of relevant new documents and comments. Given an input query, which contains event related objective aspects(e.g. actors, locations, date) and user related subjective aspects(e.g. public attention and opinion polarity), we develop a Learning-to-Rank framework to integrate aspect-level correlation between query and event. Experiments on a crawled large news corpus show the effectiveness of our proposed approach compared to several baseline models.

This paper proposes a new non-reference image quality metric that can be adopted by the state-of-the-art image/ video denoising algorithms for auto-denoising. The proposed metric is extremely simple and can be implemented in four lines of Matlab code. The basic assumption employed by the proposed metric is that the noise should be independent of the original image. A direct measurement of this dependence is, however, impractical due to the relatively low accuracy of existing denoising method. The proposed metric thus aims at maximizing the structure similarity between the input noisy image and the estimated image noise around homogeneous regions and the structure similarity between the input noisy image and the denoised image around highly-structured regions, and is computed as the linear correlation coefficient of the two corresponding structure similarity maps. Numerous experimental results demonstrate that the proposed metric not only outperforms the current state-of-the-art non-reference quality metric quantitatively and qualitatively, but also better maintains temporal coherence when used for video denoising.