Image and Feature Space Based Domain Adaptation for Vehicle Detection

The application of deep learning in the field of object detection has experienced much progress. However, due to the domain shift problem, applying an off-the-shelf detector to another domain leads to a significant performance drop. A large number of ground truth labels are required when using another domain to train models, demanding a large amount of human and financial resources. In order to avoid excessive resource requirements and performance drop caused by domain shift, this paper proposes a new domain adaptive approach to cross-domain vehicle detection. Our approach improves the cross-domain vehicle detection model from image space and feature space. We employ objectives of the generative adversarial network and cycle consistency loss for image style transfer in image space. For feature space, we align feature distributions between the source domain and the target domain to improve the detection accuracy. Experiments are carried out using the method with two different datasets, proving that this technique effectively improves the accuracy of vehicle detection in the target domain.     

A Novel Beam Search to Improve Neural Machine Translation for English-Chinese

Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, overcoming the weaknesses of conventional phrase-based translation systems. Although NMT based systems have gained their popularity in commercial translation applications, there is still plenty of room for improvement. Being the most popular search algorithm in NMT, beam search is vital to the translation result. However, traditional beam search can produce duplicate or missing translation due to its target sequence selection strategy. Aiming to alleviate this problem, this paper proposed neural machine translation improvements based on a novel beam search evaluation function. And we use reinforcement learning to train a translation evaluation system to select better candidate words for generating translations. In the experiments, we conducted extensive experiments to evaluate our methods. CASIA corpus and the 1,000,000 pairs of bilingual corpora of NiuTrans are used in our experiments. The experiment results prove that the proposed methods can effectively improve the English to Chinese translation quality.     

Passive target detection and tracking from electromagnetic field measurements

This paper presents a novel approach to the localization of moving targets in a complex environment based on the measurement of the perturbations induced by the target presence on an independently‐generated time‐varying electromagnetic field. Field perturbations are measured via a set of sensors deployed over the domain of interest and used to detect and track a possible target by resorting to a particle Bernoulli filter (PBF). To comply with real‐time operation, the PBF works along with an artificial neural network (ANN) model of the environment trained offline via finite elements (FEs). The performance of the proposed algorithm is assessed via simulation experiments.     

Coexistence of three ferroelectric phases and enhanced piezoelectric properties in BaTiO3–CaHfO3 lead-free ceramics

Perovskite ferroelectrics possess the fascinating piezoelectric properties near a morphotropic phase boundary, attributing to a low energy barrier that the results in structural instability and easy polarization rotation. In this work, a new lead-free system of (1-x)BaTiO₃-xCaHfO₃ was designed, and characterized by a coexistence of ferroelectric rhombohedral-orthorhombic-tetragonal (R-O-T) phases. With the increase amount of CaHfO₃ (x), a stable coexistence region of three ferroelectric phases (R-O-T) exists at 0.06 ≤ x ≤ 0.08. Both large piezoelectric coefficient (d₃₃～400 pC/N), inverse piezoelectric coefficient (d₃₃^*～547 pm/V) and planar electromechanical coupling factor (k_p～58.2%) can be achieved for the composition with x = 0.08 near the coexistence of three ferroelectric phases. Our results show that the materials with the composition located at a region where the three ferroelectric R-O-T phases coexist would have the lowest energy barrier and thus greatly promote the polarization rotation, resulting in a strong piezoelectric response.     

Tensor Q-rank: new data dependent definition of tensor rank

Machine Learning - Recently, the $${ Tensor}~{ Nuclear}~{ Norm}~{ (TNN)}$$ regularization based on t-SVD has been widely used in various low tubal-rank tensor recovery tasks. However, these models...     

Macrophage Immunomodulation Through New Polymers that Recapitulate Functional Effects of Itaconate as a Power House of Innate Immunity

Itaconate (ITA) is an emerging powerhouse of innate immunity with therapeutic potential that is limited in its ability to be administered in a soluble form. A library of polyester materials that incorporate ITA into polymer backbones resulting in materials with inherent immunoregulatory behavior is developed. Harnessing hydrolytic degradation release from polyester backbones, ITA polymers result in the mechanism specific immunoregulatory properties on macrophage polarization in vitro. In a functional assay, the polymer-released ITA inhibits bacterial growth on acetate. Translation to an in vivo model of biomaterial associated inflammation, intraperitoneal injection of ITA polymers demonstrate a rapid resolution of inflammation in comparison to a control polymer silicone, demonstrating the value of sustained biomimetic presentation of ITA.