Convolutional neural networks (CNNs) have proven highly effective at image
synthesis and style transfer. For most users, however, using them as tools can
be a challenging task due to their unpredictable behavior that goes against
common intuitions. This paper introduces a novel concept to augment such
generative architectures with semantic annotations, either by manually
authoring pixel labels or using existing solutions for semantic segmentation.
The result is a content-aware generative algorithm that offers meaningful
control over the outcome. Thus, we increase the quality of images generated by
avoiding common glitches, make the results look significantly more plausible,
and extend the functional range of these algorithms---whether for portraits or
landscapes, etc. Applications include semantic style transfer and turning
doodles with few colors into masterful paintings!

本文提出了一种新概念，即通过手动制作像素标签或使用现有解决方案进行语义分割，将生成式架构与语义注释相结合，从而增强生成算法的内容感知性，提高生成的图像质量，避免常见的故障，并扩展这些算法的功能范围。

语义风格转换：将草图变为艺术品

Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks

In many robotic domains such as flexible automated manufacturing or personal
assistance, a fundamental perception task is that of identifying and localizing
objects whose 3D models are known. Canonical approaches to this problem include
discriminative methods that find correspondences between feature descriptors
computed over the model and observed data. While these methods have been
employed successfully, they can be unreliable when the feature descriptors fail
to capture variations in observed data; a classic cause being occlusion. As a
step towards deliberative reasoning, we present PERCH: PErception via SeaRCH,
an algorithm that seeks to find the best explanation of the observed sensor
data by hypothesizing possible scenes in a generative fashion. Our
contributions are: i) formulating the multi-object recognition and localization
task as an optimization problem over the space of hypothesized scenes, ii)
exploiting structure in the optimization to cast it as a combinatorial search
problem on what we call the Monotone Scene Generation Tree, and iii) leveraging
parallelization and recent advances in multi-heuristic search in making
combinatorial search tractable. We prove that our system can guaranteedly
produce the best explanation of the scene under the chosen cost function, and
validate our claims on real world RGB-D test data. Our experimental results
show that we can identify and localize objects under heavy occlusion--cases
where state-of-the-art methods struggle.

本文介绍了一种名为 PERCH 的算法，它通过产生可能性场景，寻找最佳的传感器数据解释，解决了多物体识别和定位任务中常见的遮挡问题，并在实际 RGB-D 测试数据上验证了其优越性。

基于搜索的多目标感知与定位

PERCH: Perception via Search for Multi-Object Recognition and  Localization

In a recent work [Proc. Natl. Acad. Sci. USA 108, 3838 (2011)], Schneider et
al. proposed a new measure for network robustness and investigated optimal
networks with respect to this quantity. For networks with a power-law degree
distribution, the optimized networks have an onion structure-high-degree
vertices forming a core with radially decreasing degrees and an
over-representation of edges within the same radial layer. In this paper we
relate the onion structure to graphs with good expander properties (another
characterization of robust network) and argue that networks of skewed degree
distributions with large spectral gaps (and thus good expander properties) are
typically onion structured. Furthermore, we propose a generative algorithm
producing synthetic scale-free networks with onion structure, circumventing the
optimization procedure of Schneider et al. We validate the robustness of our
generated networks against malicious attacks and random removals.

研究网络的鲁棒性和最优网络构建方法，并发现了具有好的展开特性的网络通常具有洋葱状结构，提出了一种生成具有洋葱状结构的复杂网络的算法，并对生成的网络进行了攻击和随机删除的稳健性验证。