Search

A predefined permission source region (PSR) is commonly used in bioluminescence tomography (BLT) as a priori information to reduce the ill-posedness of source reconstruction. However, the PSR is usually hard to determine and may miss the actual source region. Simultaneously, a linear or nonlinear based reconstruction method commonly have a relatively poor performance in the terms of low photon rate and strong noise. Here, we propose an alternative statistical-based-reconstruction framework with a cluster-algorithm-optimized PSR for BLT. In the alternative reconstruction framework, a global reconstruction is first conducted overall the solving domain to generate a rough estimation of source distribution by using a global based maximum likelihood expectation maximum (MLEM) method. Subsequently, a k-means cluster method is used to learn and find likely source support regions, which generates the optimal PSR. Finally, a local MLEM based reconstruction is performed to refine the source distribution on the optimal PSR. We first verify the performance of the proposed method with a series of numerical simulations, and then explore the potential by imaging in situ liver cancer in living mouse. [ABSTRACT FROM AUTHOR]

Web-scale image understanding is drawing more and more attention from the computer vision and multimedia domain. To solve the key problem of visual polysemia and concept polymorphism in the image understanding, this paper proposes a semantic dictionary to describe the images on the level of semantic. The semantic dictionary characterizes the probability distribution between visual appearances and semantic concepts, and the learning procedure of semantic dictionary is formulated into a minimization optimization problem. Mixed-norm regularization is adopted to solve the above optimization for learning the concept membership distribution of visual appearance. Furthermore, to improve the generalization ability of the semantic description, we propose the semantic expansion technology, where a concept transferring matrix is learnt to quantize the implicit relevancy among the concepts. Finally, the distributed framework on the basis of the semantic dictionary is constructed to speed up the large scale image understanding. The semantic dictionary is validated in the tasks of large scale semantic image search and image annotation. [ABSTRACT FROM AUTHOR]

Time-interleaving has been a popular choice for multi-GHz analog-to-digital converters (ADCs). Unfortunately, inherent defects such as offset, gain, timing-skew mismatches among sub-ADCs degrade overall performance seriously. At present, the method for eliminating offset and gain mismatch is fairly straightforward, however, calibration for timing-skew is still in a state of exploration. An efficient digital-mixing-based method to estimate timing skew in time-interleaved analog-to-digital converters (TI-ADCs) is proposed and verified. The timing skew can be estimated by digital-mixing and inverse sine function processing. The proposed method can greatly alleviate the effects of phase ambiguity. It is also insensitive to offset mismatch. A four-channel TI-ADC behavioral system of 10-bits 2 GS/s has been simulated to verify the performance of the method. Simulation results demonstrate that the method greatly improves the TI-ADC′s performance and is effective up to the severe timing skew mismatch. [ABSTRACT FROM AUTHOR]

Aerial-view geo-localization tends to determine an unknown position through matching the drone-view image with the geo-tagged satellite-view image. This task is mostly regarded as an image retrieval problem. The key underpinning this task is to design a series of deep neural networks to learn discriminative image descriptors. However, existing methods meet large performance drops under realistic weather, such as rain and fog, since they do not take the domain shift between the training data and multiple test environments into consideration. To minor this domain gap, we propose a Multiple-environment Self-adaptive Network (MuSe-Net) to dynamically adjust the domain shift caused by environmental changing. In particular, MuSe-Net employs a two-branch neural network containing one multiple-environment style extraction network and one self-adaptive feature extraction network. As the name implies, the multiple-environment style extraction network is to extract the environment-related style information, while the self-adaptive feature extraction network utilizes an adaptive modulation module to dynamically minimize the environment-related style gap. Extensive experiments on three widely-used benchmarks, i.e. , University-1652, SUES-200, and CVUSA, demonstrate that the proposed MuSe-Net achieves a competitive result for geo-localization in multiple environments. Furthermore, we observe that the proposed method also shows great potential to the unseen extreme weather, such as mixing the fog, rain and snow. • Identifying one key challenge in visual geo-localization: weather and illumination changes. • Presenting MuSe-Net to alleviate the interference caused by environmental changes. • Designing Residual SPADE for efficient training and feature discrimination boosting. • Results on three geo-localization benchmarks confirm the superiority of our MuSe-Net. [ABSTRACT FROM AUTHOR]

Multi-source Unsupervised Domain Adaptation (MUDA) transfers knowledge learned from multiple labeled source domains to an unlabeled target domain by minimizing the domain shift between multiple source domains and the target domain. Recent studies on MUDA have focused on aligning the distribution of each pair of source and target domains in separate feature spaces to reduce their domain shift. However, these approaches suffer from two main shortcomings. First, they usually focus on the global domain shift which lacks consideration of the joint distribution of category-corresponded subdomains. Second, out-of-distribution samples far from the sample center are hard to align by the global domain alignment. Therefore, we propose a novel Deep Joint Semantic Adaptive Network (DJSAN) for MUDA. Specifically, a new maximum mean discrepancy-based metric, Joint Semantic Maximum Mean Discrepancy (JSMMD), is proposed, which can uniformly optimize the cross-domain joint distribution of category-corresponded subdomains on multiple task-specific layers. Moreover, to deal with the out-of-distribution hard samples, we propose an across-domain data augmentation method called Source-Target Domain Mixing (STDMix) to enhance the robustness of the model, which synthesizes the source domain and target domain into a new domain at a fixed ratio and utilizes information entropy to provide reliable pseudo-labels for samples in the target domain. Experimental results on three public datasets, i.e., Office-31, Digits-five, and Office-Home, show that our proposed method achieves improvements of 0.3%, 1.8%, and 2.7% in average accuracy, respectively. • We propose a simple and effective multi-source unsupervised domain adaptation method for classification. • We propose a metric to align the cross-domain joint distribution of category-corresponded subdomains on multiple task-specific layers. • We propose a cross-domain data augmentation method to handle out- of-distribution hard samples. • Experiment results show that our proposed method achieves state-of-the-art performance on multiple domain adaptation datasets. [ABSTRACT FROM AUTHOR]

This paper addresses the issue of noise interference in road defect detection, caused by various environmental factors or acquisition equipment. In this article, we add three different levels of salt & pepper noise to the road defect dataset and propose a novel anti-noise dual-branch network (ADNet). The proposed ADNet leverages two backbone networks equipped with the dual-branch interaction (DI) modules to learn the defect information from noise and clear images for improving noise immunity. Then, the weighted feature representation (WFR) module is designed to extract more context-aware cues from the multi-level feature. Additionally, the region perception unit is proposed, where channel-spatial attention optimization (CSAO) module extracts more defect region information by utilizing the attention mechanism and multi-scale refinement (MR) optimizes the boundary information with the U-Net structure. Extensive experimental results demonstrate that the proposed method outperforms state-of-the-art methods, making it a promising solution for detecting road defects in noisy environments. [ABSTRACT FROM AUTHOR]

Salient object detection methods based on two-modal images have achieved remarkable success with the aid of image acquisition equipment. However, environmental factors often interfere with the Depth and Thermal maps, rendering them ineffective in providing object information. To address this weakness, we utilize the VDT dataset, which includes Visible, Depth, and Thermal images, and propose a triple-modal interaction encoder and multi-scale fusion decoder network (TMNet) to highlight the salient regions. The triple-modal interaction encoder comprises the separation context-aware feature module, channel-wise fusion module, and triple-modal refinement and fusion module, enabling us to fully explore and utilize the complementarity between Visible, Depth, and Thermal information. The multi-scale fusion decoder involves the semantic-aware localizing module and contour-aware refinement module to extract and fuse the location and boundary information, yielding a high-quality saliency map. Extensive experiments on the public VDT-2048 dataset demonstrate that our TMNet outperforms existing state-of-the-art methods in terms of all evaluation metrics. • This paper proposes a triple-modal interaction encoder and multi-scale fusion decoder network (TMNet) to highlight the salient regions. • The triple-modal interaction encoder comprises the separation context-aware feature module, channel-wise fusion module, and triple-modal refinement and fusion module to explore and utilize the complementarity between Visible, Depth, and Thermal information. • The multi-scale fusion decoder involves the semantic-aware localizing module and contour-aware refinement module to extract and fuse the location and boundary information, yielding a high-quality saliency map. • Extensive experiments on the public VDT-2048 dataset demonstrate that our TMNet outperforms existing state-of-the-art methods in terms of all evaluation metrics. [ABSTRACT FROM AUTHOR]

• We annotate attribute labels on two large-scale person re-identification datasets. • We propose APR to improve re-ID by exploiting global and detailed information. • We introduce a module to leverage the correlation between attributes. • We speed-up the retrieval of re-ID by ten times with only a 2.92% accuracy drop. • We achieve competitive re-ID performance with the state-of-the-art methods. Person re-identification (re-ID) and attribute recognition share a common target at learning pedestrian descriptions. Their difference consists in the granularity. Most existing re-ID methods only take identity labels of pedestrians into consideration. However, we find the attributes, containing detailed local descriptions, are beneficial in allowing the re-ID model to learn more discriminative feature representations. In this paper, based on the complementarity of attribute labels and ID labels, we propose an attribute-person recognition (APR) network, a multi-task network which learns a re-ID embedding and at the same time predicts pedestrian attributes. We manually annotate attribute labels for two large-scale re-ID datasets, and systematically investigate how person re-ID and attribute recognition benefit from each other. In addition, we re-weight the attribute predictions considering the dependencies and correlations among the attributes. The experimental results on two large-scale re-ID benchmarks demonstrate that by learning a more discriminative representation, APR achieves competitive re-ID performance compared with the state-of-the-art methods. We use APR to speed up the retrieval process by ten times with a minor accuracy drop of 2.92% on Market-1501. Besides, we also apply APR on the attribute recognition task and demonstrate improvement over the baselines. [ABSTRACT FROM AUTHOR]

To boost the product quality, numerous saliency-based surface defect detection methods have been devoted to the areas of industrial production, construction consumable, road construction. However, the existing salient object detection (SOD) methods not only consume a significant amount of computing resources but also fail to meet the detection efficiency requirements of enterprises. Therefore, this paper proposes a lightweight semantics-aware multi-level feature interaction network (SMINet), to address the above issues. In the encoder phase, we integrate multiple adjacent level features in the cross-layer feature fusion (CFF) module to alleviate the discrepancy between multi-scale features. In the decoder phase, we first employ the semantic-aware feature extraction (SFE) module to mine the location cues embedded in the high-level features. Afterwards, we introduce the detail-aware context attention (DCA) module based on the attention mechanism to recover more spatial details. Extensive experiments on four surface defect datasets validate that our SMINet outperforms the existing state-of-the-art methods. [ABSTRACT FROM AUTHOR]