ID 原文 译文
25215 当目标领域缺少足够多的标注数据时，迁移学习利用相关源领域的标注数据，辅助提升目标域的学习性能，但是目标域与源域的数据通常不满足独立同分布，容易导致“负迁移”问题。 With enough labeled data lacking in the target domain, it works well for transfer learning to use the labeled data of the related source domain and help improve the learning performance of the target domain. However, the data of these two domains usually do not satisfy the independently identically distribution, which easily leads to the problem of "negative transfer"．
25216 本文在有监督主题模型(SupervisedLDA，SLDA)的基础上，融合迁移学习方法提出一种共享主题知识的迁移主题模型(Transfer SLDA，Tr-SLDA)，提出 Tr-SLDA-Gibbs 主题采样新方法，在类别标签的约束下对不同领域文档中的词采取不同的采样策略，且无需指定主题个数。 Tr-SLDA (Transfer SLDA), a transfer topic model based on supervised topic model (Supervised LDA, SLDA) is proposed, which shares topic knowledge by integrating transfer learning. A Tr-SLDA-Gibbs sampling method is proposed, under the constraints of category labels, different sampling strategies are adopted for words in the documents of different domains without specifying the number of topics．
25217 辅助源域与目标域共享潜在主题空间，Tr-SLDA 通过发现潜在共享主题与不同领域类别之间的语义关联从源域迁移知识，可以有效解决“负迁移”问题。 The source domain and target domain share the potential topic space, Tr-SLDA can effectively solve the problem of "negative transfer" by discovering the semantic correlation between the potential shared topics and categories of different domains．
25218 基于 Tr-SLDA 迁移主题模型提出 Tr-SLDA-TC(Tr-SLDA Text Categorization)文本分类方法。 The Tr-SLDA-TC (Tr-SLDA-Text Categorization) text classification method is proposed based on the Tr-SLDA model．
25219 对比实验表明，该方法可有效利用源域知识来提高目标领域的分类性能。 The comprehensive experiments show that the proposed method can effectively improve the performance of the classification by utilizing the knowledge from the source domain．
25220 场景图像分割一直是机器视觉学习中较为复杂的重难点问题。 Scene segmentation has always been a key and complicated problem in machine learning．
25221 本文在机器视觉注意力机制学习方法的基础上，融合人类对事物个体的认知，提出场景对象的 Focus + Context 语义表征，将对象类别信息带入图像底层特征学习中，运用概率统计理论，在抽象层上建模局部区域对象，再联合上下文语义信息推理全局与局部区域对象之间的关系，以实现类内焦点对象(Focus)突出的场景语义分割。 In order to understand the scene and recognize the objects more accurately, this paper adopts human attention mechanism, takes the category semantic information into consideration and merges it into the image feature learning. The Focus + Context semantic representation is proposed, where the context describes the relationship between the focus and different objects in the scene, and the focus shared among the same category are composed of similar clusters. The probabilistic topic model is used to compute the local features as well as their semantic information.
25222 实验验证，基于 Focus + Context 的语义表征和建模能够增加对象的识别率，尤其是在小样本环境下，所提出的方法能极大地简化场景的理解。 The experimental results show that the Focus + Context method increases the recognition rate of the scene objects, and specially, the proposed method, in a local and global understanding way, can simplify the scene recognition greatly under a small sample size．
25223 针对现有移频干扰对抗方法，分析得出基于回波匹配输出中心频率鉴别干扰适用范围有限、调频斜率捷变 LFM(Slope Varying LFM，SV-LFM)波形能够一定程度抑制干扰，但需设计合理捷变方式的结论。 By studying the existing methods for countering frequency-shift jamming, this paper comes to the conclusion that the applicability of jamming discrimination method based on echo matching output center-frequency is limited and slope varying LFM(SV-LFM), a radar transmitting waveform, can suppress the jamming to some extent, if the agile way is designed reasonable．
25224 同时，以 LFM 脉冲多普勒雷达抗自卫式移频干扰为背景，提出联合相参积累和二维分数阶傅里叶变换(Two Dimensional FractionalFourier Transform，2D-FＲFT)干扰鉴别方法，根据回波信号在两种处理方式下的峰值差异，对比门限鉴别目标真伪。 Meanwhile, a jamming discrimination method jointing coherent integration and two dimensional fractional Fourier transform (2D-FＲFT) is proposed on the background of LFM pulse Doppler radar countering self-screening frequency-shift jamming. According to the peak value difference of echo signal under the two processing modes, true and false targets are identified by comparing with a setting threshold．