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.     

Investigation on milling force of thin-walled workpiece considering dynamic characteristics of workpiece

Journal of Mechanical Science and Technology - The idea of integral calculus is used in traditional milling force prediction methods. In the traditional method, the milling cutter is divided into...     

A quarter century of wine pigment discovery

The red grape berry pigments, anthocyanins, were characterized in the early 20th century, but investigations of wine pigments were stymied during that era. The question of their identity was a major challenge for wine chemists. A number of techniques showed that the pigments were polymeric in nature. Some structures were postulated by mid-century based on reactions between anthocyanins and condensed tannin, and later postulated wine pigments were observed in model reactions. Some related compounds were then observed in wine. By the end of the 20th century, the ionization of non-volatiles for mass spectrometry opened the door to these compounds. In addition, a new class of compounds was observed, the pyranoanthocyanins, a product of fermentation and aging metabolites with anthocyanins. These compounds possess the pigment stability to SO₂ and pH change that is characteristic of aged red wine. Aging experiments show a dynamic situation with shifts in the population of pigment classes over time. The very large number of diverse pigments explains why it has been so difficult to answer the century-old question of the structure of wine pigments. Our current understanding is founded on the use of mass spectral analysis using electrospray and related ionization techniques over the last 25 years. Future progress will rely on more sophisticated analysis of this very complex mixture of substances. © 2019 Society of Chemical Industry